diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ice')
45 files changed, 5220 insertions, 1392 deletions
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 817977e3039d..960277d78e09 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -47,5 +47,5 @@ ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o -ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o +ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o ice_eswitch_br.o ice-$(CONFIG_GNSS) += ice_gnss.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4ba3d99439a0..5022b036ca4f 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -200,6 +200,8 @@ enum ice_feature { ICE_F_PTP_EXTTS, ICE_F_SMA_CTRL, ICE_F_GNSS, + ICE_F_ROCE_LAG, + ICE_F_SRIOV_LAG, ICE_F_MAX }; @@ -370,6 +372,7 @@ struct ice_vsi { u16 rx_buf_len; struct ice_aqc_vsi_props info; /* VSI properties */ + struct ice_vsi_vlan_info vlan_info; /* vlan config to be restored */ /* VSI stats */ struct rtnl_link_stats64 net_stats; @@ -517,6 +520,7 @@ enum ice_misc_thread_tasks { struct ice_switchdev_info { struct ice_vsi *control_vsi; struct ice_vsi *uplink_vsi; + struct ice_esw_br_offloads *br_offloads; bool is_running; }; @@ -567,6 +571,7 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ struct mutex adev_mutex; /* lock to protect aux device access */ + struct mutex lag_mutex; /* protect ice_lag struct in PF */ u32 msg_enable; struct ice_ptp ptp; struct gnss_serial *gnss_serial; @@ -626,6 +631,7 @@ struct ice_pf { struct ice_lag *lag; /* Link Aggregation information */ struct ice_switchdev_info switchdev; + struct ice_esw_br_port *br_port; #define ICE_INVALID_AGG_NODE_ID 0 #define ICE_PF_AGG_NODE_ID_START 1 @@ -636,6 +642,8 @@ struct ice_pf { struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES]; }; +extern struct workqueue_struct *ice_lag_wq; + struct ice_netdev_priv { struct ice_vsi *vsi; struct ice_repr *repr; @@ -853,7 +861,7 @@ static inline bool ice_is_adq_active(struct ice_pf *pf) return false; } -bool netif_is_ice(struct net_device *dev); +bool netif_is_ice(const struct net_device *dev); int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); int ice_vsi_open_ctrl(struct ice_vsi *vsi); @@ -909,8 +917,25 @@ void ice_fdir_release_flows(struct ice_hw *hw); void ice_fdir_replay_flows(struct ice_hw *hw); void ice_fdir_replay_fltrs(struct ice_pf *pf); int ice_fdir_create_dflt_rules(struct ice_pf *pf); -int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, - struct ice_rq_event_info *event); + +enum ice_aq_task_state { + ICE_AQ_TASK_NOT_PREPARED, + ICE_AQ_TASK_WAITING, + ICE_AQ_TASK_COMPLETE, + ICE_AQ_TASK_CANCELED, +}; + +struct ice_aq_task { + struct hlist_node entry; + struct ice_rq_event_info event; + enum ice_aq_task_state state; + u16 opcode; +}; + +void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task, + u16 opcode); +int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task, + unsigned long timeout); int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 63d3e1dcbba5..29f7a9852aec 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -120,6 +120,9 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE 0x0076 #define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT 0x0077 #define ICE_AQC_CAPS_NVM_MGMT 0x0080 +#define ICE_AQC_CAPS_FW_LAG_SUPPORT 0x0092 +#define ICE_AQC_BIT_ROCEV2_LAG 0x01 +#define ICE_AQC_BIT_SRIOV_LAG 0x02 u8 major_ver; u8 minor_ver; @@ -232,6 +235,8 @@ struct ice_aqc_set_port_params { #define ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA BIT(2) __le16 bad_frame_vsi; __le16 swid; +#define ICE_AQC_PORT_SWID_VALID BIT(15) +#define ICE_AQC_PORT_SWID_M 0xFF u8 reserved[10]; }; @@ -241,10 +246,12 @@ struct ice_aqc_set_port_params { * Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) * Get Allocated Resource Descriptors Command (indirect 0x020A) + * Share Resource command (indirect 0x020B) */ #define ICE_AQC_RES_TYPE_VSI_LIST_REP 0x03 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE 0x04 #define ICE_AQC_RES_TYPE_RECIPE 0x05 +#define ICE_AQC_RES_TYPE_SWID 0x07 #define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK 0x21 #define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES 0x22 #define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES 0x23 @@ -264,6 +271,7 @@ struct ice_aqc_set_port_params { /* Allocate Resources command (indirect 0x0208) * Free Resources command (indirect 0x0209) + * Share Resource command (indirect 0x020B) */ struct ice_aqc_alloc_free_res_cmd { __le16 num_entries; /* Number of Resource entries */ @@ -818,7 +826,11 @@ struct ice_aqc_txsched_move_grp_info_hdr { __le32 src_parent_teid; __le32 dest_parent_teid; __le16 num_elems; - __le16 reserved; + u8 mode; +#define ICE_AQC_MOVE_ELEM_MODE_SAME_PF 0x0 +#define ICE_AQC_MOVE_ELEM_MODE_GIVE_OWN 0x1 +#define ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN 0x2 + u8 reserved; }; struct ice_aqc_move_elem { @@ -1392,6 +1404,7 @@ struct ice_aqc_get_link_topo { struct ice_aqc_link_topo_addr addr; u8 node_part_num; #define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_C827 0x31 u8 rsvd[9]; }; @@ -1781,11 +1794,10 @@ struct ice_aqc_lldp_filter_ctrl { u8 reserved2[12]; }; +#define ICE_AQC_RSS_VSI_VALID BIT(15) + /* Get/Set RSS key (indirect 0x0B04/0x0B02) */ struct ice_aqc_get_set_rss_key { -#define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15) -#define ICE_AQC_GSET_RSS_KEY_VSI_ID_S 0 -#define ICE_AQC_GSET_RSS_KEY_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_KEY_VSI_ID_S) __le16 vsi_id; u8 reserved[6]; __le32 addr_high; @@ -1803,35 +1815,33 @@ struct ice_aqc_get_set_rss_keys { u8 extended_hash_key[ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE]; }; -/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */ -struct ice_aqc_get_set_rss_lut { -#define ICE_AQC_GSET_RSS_LUT_VSI_VALID BIT(15) -#define ICE_AQC_GSET_RSS_LUT_VSI_ID_S 0 -#define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x3FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S) - __le16 vsi_id; -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M \ - (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) - -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF 1 -#define ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL 2 +enum ice_lut_type { + ICE_LUT_VSI = 0, + ICE_LUT_PF = 1, + ICE_LUT_GLOBAL = 2, +}; -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S 2 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M \ - (0x3 << ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) +enum ice_lut_size { + ICE_LUT_VSI_SIZE = 64, + ICE_LUT_GLOBAL_SIZE = 512, + ICE_LUT_PF_SIZE = 2048, +}; -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128 128 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128_FLAG 0 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512 512 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG 1 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K 2048 -#define ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG 2 +/* enum ice_aqc_lut_flags combines constants used to fill + * &ice_aqc_get_set_rss_lut ::flags, which is an amalgamation of global LUT ID, + * LUT size and LUT type, last of which does not need neither shift nor mask. + */ +enum ice_aqc_lut_flags { + ICE_AQC_LUT_SIZE_SMALL = 0, /* size = 64 or 128 */ + ICE_AQC_LUT_SIZE_512 = BIT(2), + ICE_AQC_LUT_SIZE_2K = BIT(3), -#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S 4 -#define ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M \ - (0xF << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) + ICE_AQC_LUT_GLOBAL_IDX = GENMASK(7, 4), +}; +/* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */ +struct ice_aqc_get_set_rss_lut { + __le16 vsi_id; __le16 flags; __le32 reserved; __le32 addr_high; @@ -1923,6 +1933,42 @@ struct ice_aqc_dis_txq_item { __le16 q_id[]; } __packed; +/* Move/Reconfigure Tx queue (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs { + u8 cmd_type; +#define ICE_AQC_Q_CFG_MOVE_NODE 0x1 +#define ICE_AQC_Q_CFG_TC_CHNG 0x2 +#define ICE_AQC_Q_CFG_MOVE_TC_CHNG 0x3 +#define ICE_AQC_Q_CFG_SUBSEQ_CALL BIT(2) +#define ICE_AQC_Q_CFG_FLUSH BIT(3) + u8 num_qs; + u8 port_num_chng; +#define ICE_AQC_Q_CFG_SRC_PRT_M 0x7 +#define ICE_AQC_Q_CFG_DST_PRT_S 3 +#define ICE_AQC_Q_CFG_DST_PRT_M (0x7 << ICE_AQC_Q_CFG_DST_PRT_S) + u8 time_out; +#define ICE_AQC_Q_CFG_TIMEOUT_S 2 +#define ICE_AQC_Q_CFG_TIMEOUT_M (0x1F << ICE_AQC_Q_CFG_TIMEOUT_S) + __le32 blocked_cgds; + __le32 addr_high; + __le32 addr_low; +}; + +/* Per Q struct for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txq_perq { + __le16 q_handle; + u8 tc; + u8 rsvd; + __le32 q_teid; +}; + +/* The buffer for Move/Reconfigure Tx LAN Queues (indirect 0x0C32) */ +struct ice_aqc_cfg_txqs_buf { + __le32 src_parent_teid; + __le32 dst_parent_teid; + struct ice_aqc_cfg_txq_perq queue_info[]; +}; + /* Add Tx RDMA Queue Set (indirect 0x0C33) */ struct ice_aqc_add_rdma_qset { u8 num_qset_grps; @@ -2181,6 +2227,7 @@ struct ice_aq_desc { struct ice_aqc_neigh_dev_req neigh_dev; struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; + struct ice_aqc_cfg_txqs cfg_txqs; struct ice_aqc_add_rdma_qset add_rdma_qset; struct ice_aqc_add_get_update_free_vsi vsi_cmd; struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; @@ -2263,6 +2310,7 @@ enum ice_adminq_opc { /* Alloc/Free/Get Resources */ ice_aqc_opc_alloc_res = 0x0208, ice_aqc_opc_free_res = 0x0209, + ice_aqc_opc_share_res = 0x020B, ice_aqc_opc_set_vlan_mode_parameters = 0x020C, ice_aqc_opc_get_vlan_mode_parameters = 0x020D, @@ -2356,6 +2404,7 @@ enum ice_adminq_opc { /* Tx queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + ice_aqc_opc_cfg_txqs = 0x0C32, ice_aqc_opc_add_rdma_qset = 0x0C33, /* package commands */ diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 4a12316f7b46..7fa43827a3f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -408,7 +408,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) */ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) { - int chain_len = ICE_MAX_CHAINED_RX_BUFS; struct ice_vsi *vsi = ring->vsi; u32 rxdid = ICE_RXDID_FLEX_NIC; struct ice_rlan_ctx rlan_ctx; @@ -435,7 +434,8 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Receive Packet Data Buffer Size. * The Packet Data Buffer Size is defined in 128 byte units. */ - rlan_ctx.dbuf = ring->rx_buf_len >> ICE_RLAN_CTX_DBUF_S; + rlan_ctx.dbuf = DIV_ROUND_UP(ring->rx_buf_len, + BIT_ULL(ICE_RLAN_CTX_DBUF_S)); /* use 32 byte descriptors */ rlan_ctx.dsize = 1; @@ -472,17 +472,11 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ rlan_ctx.showiv = 0; - /* For AF_XDP ZC, we disallow packets to span on - * multiple buffers, thus letting us skip that - * handling in the fast-path. - */ - if (ring->xsk_pool) - chain_len = 1; /* Max packet size for this queue - must not be set to a larger value * than 5 x DBUF */ rlan_ctx.rxmax = min_t(u32, vsi->max_frame, - chain_len * ring->rx_buf_len); + ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len); /* Rx queue threshold in units of 64 */ rlan_ctx.lrxqthresh = 1; @@ -800,6 +794,8 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, v_idx) ice_free_q_vector(vsi, v_idx); + + vsi->num_q_vectors = 0; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index e16d4c83ed5f..80deca45ab59 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5,6 +5,7 @@ #include "ice_sched.h" #include "ice_adminq_cmd.h" #include "ice_flow.h" +#include "ice_ptp_hw.h" #define ICE_PF_RESET_WAIT_COUNT 300 @@ -1999,37 +2000,31 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) /** * ice_aq_alloc_free_res - command to allocate/free resources * @hw: pointer to the HW struct - * @num_entries: number of resource entries in buffer * @buf: Indirect buffer to hold data parameters and response * @buf_size: size of buffer for indirect commands * @opc: pass in the command opcode - * @cd: pointer to command details structure or NULL * * Helper function to allocate/free resources using the admin queue commands */ -int -ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, - struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, - enum ice_adminq_opc opc, struct ice_sq_cd *cd) +int ice_aq_alloc_free_res(struct ice_hw *hw, + struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, + enum ice_adminq_opc opc) { struct ice_aqc_alloc_free_res_cmd *cmd; struct ice_aq_desc desc; cmd = &desc.params.sw_res_ctrl; - if (!buf) - return -EINVAL; - - if (buf_size < flex_array_size(buf, elem, num_entries)) + if (!buf || buf_size < flex_array_size(buf, elem, 1)) return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, opc); desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - cmd->num_entries = cpu_to_le16(num_entries); + cmd->num_entries = cpu_to_le16(1); - return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + return ice_aq_send_cmd(hw, &desc, buf, buf_size, NULL); } /** @@ -2059,8 +2054,7 @@ ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res) if (btm) buf->res_type |= cpu_to_le16(ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) goto ice_alloc_res_exit; @@ -2094,8 +2088,7 @@ int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res) buf->res_type = cpu_to_le16(type); memcpy(buf->elem, res, sizeof(*buf->elem) * num); - status = ice_aq_alloc_free_res(hw, num, buf, buf_len, - ice_aqc_opc_free_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); if (status) ice_debug(hw, ICE_DBG_SW, "CQ CMD Buffer:\n"); @@ -2241,6 +2234,14 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, "%s: reset_restrict_support = %d\n", prefix, caps->reset_restrict_support); break; + case ICE_AQC_CAPS_FW_LAG_SUPPORT: + caps->roce_lag = !!(number & ICE_AQC_BIT_ROCEV2_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: roce_lag = %u\n", + prefix, caps->roce_lag); + caps->sriov_lag = !!(number & ICE_AQC_BIT_SRIOV_LAG); + ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n", + prefix, caps->sriov_lag); + break; default: /* Not one of the recognized common capabilities */ found = false; @@ -2654,6 +2655,67 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, } /** + * ice_aq_get_netlist_node + * @hw: pointer to the hw struct + * @cmd: get_link_topo AQ structure + * @node_part_number: output node part number if node found + * @node_handle: output node handle parameter if node found + */ +static int +ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, + u8 *node_part_number, u16 *node_handle) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + desc.params.get_link_topo = *cmd; + + if (ice_aq_send_cmd(hw, &desc, NULL, 0, NULL)) + return -EIO; + + if (node_handle) + *node_handle = le16_to_cpu(desc.params.get_link_topo.addr.handle); + if (node_part_number) + *node_part_number = desc.params.get_link_topo.node_part_num; + + return 0; +} + +/** + * ice_is_pf_c827 - check if pf contains c827 phy + * @hw: pointer to the hw struct + */ +bool ice_is_pf_c827(struct ice_hw *hw) +{ + struct ice_aqc_get_link_topo cmd = {}; + u8 node_part_number; + u16 node_handle; + int status; + + if (hw->mac_type != ICE_MAC_E810) + return false; + + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) + return true; + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); + cmd.addr.topo_params.index = 0; + + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) + return false; + + if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) + return true; + + return false; +} + +/** * ice_aq_list_caps - query function/device capabilities * @hw: pointer to the HW struct * @buf: a buffer to hold the capabilities @@ -3869,6 +3931,34 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, return status; } +static enum ice_lut_size ice_lut_type_to_size(enum ice_lut_type type) +{ + switch (type) { + case ICE_LUT_VSI: + return ICE_LUT_VSI_SIZE; + case ICE_LUT_GLOBAL: + return ICE_LUT_GLOBAL_SIZE; + case ICE_LUT_PF: + return ICE_LUT_PF_SIZE; + } + WARN_ONCE(1, "incorrect type passed"); + return ICE_LUT_VSI_SIZE; +} + +static enum ice_aqc_lut_flags ice_lut_size_to_flag(enum ice_lut_size size) +{ + switch (size) { + case ICE_LUT_VSI_SIZE: + return ICE_AQC_LUT_SIZE_SMALL; + case ICE_LUT_GLOBAL_SIZE: + return ICE_AQC_LUT_SIZE_512; + case ICE_LUT_PF_SIZE: + return ICE_AQC_LUT_SIZE_2K; + } + WARN_ONCE(1, "incorrect size passed"); + return 0; +} + /** * __ice_aq_get_set_rss_lut * @hw: pointer to the hardware structure @@ -3878,95 +3968,44 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, * Internal function to get (0x0B05) or set (0x0B03) RSS look up table */ static int -__ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *params, bool set) -{ - u16 flags = 0, vsi_id, lut_type, lut_size, glob_lut_idx, vsi_handle; - struct ice_aqc_get_set_rss_lut *cmd_resp; +__ice_aq_get_set_rss_lut(struct ice_hw *hw, + struct ice_aq_get_set_rss_lut_params *params, bool set) +{ + u16 opcode, vsi_id, vsi_handle = params->vsi_handle, glob_lut_idx = 0; + enum ice_lut_type lut_type = params->lut_type; + struct ice_aqc_get_set_rss_lut *desc_params; + enum ice_aqc_lut_flags flags; + enum ice_lut_size lut_size; struct ice_aq_desc desc; - int status; - u8 *lut; + u8 *lut = params->lut; - if (!params) - return -EINVAL; - - vsi_handle = params->vsi_handle; - lut = params->lut; - if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) + if (!lut || !ice_is_vsi_valid(hw, vsi_handle)) return -EINVAL; - lut_size = params->lut_size; - lut_type = params->lut_type; - glob_lut_idx = params->global_lut_id; - vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - - cmd_resp = &desc.params.get_set_rss_lut; + lut_size = ice_lut_type_to_size(lut_type); + if (lut_size > params->lut_size) + return -EINVAL; + else if (set && lut_size != params->lut_size) + return -EINVAL; - if (set) { - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_lut); + opcode = set ? ice_aqc_opc_set_rss_lut : ice_aqc_opc_get_rss_lut; + ice_fill_dflt_direct_cmd_desc(&desc, opcode); + if (set) desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - } else { - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_lut); - } - - cmd_resp->vsi_id = cpu_to_le16(((vsi_id << - ICE_AQC_GSET_RSS_LUT_VSI_ID_S) & - ICE_AQC_GSET_RSS_LUT_VSI_ID_M) | - ICE_AQC_GSET_RSS_LUT_VSI_VALID); - - switch (lut_type) { - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI: - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF: - case ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL: - flags |= ((lut_type << ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M); - break; - default: - status = -EINVAL; - goto ice_aq_get_set_rss_lut_exit; - } - - if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_GLOBAL) { - flags |= ((glob_lut_idx << ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_S) & - ICE_AQC_GSET_RSS_LUT_GLOBAL_IDX_M); - if (!set) - goto ice_aq_get_set_rss_lut_send; - } else if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) { - if (!set) - goto ice_aq_get_set_rss_lut_send; - } else { - goto ice_aq_get_set_rss_lut_send; - } + desc_params = &desc.params.get_set_rss_lut; + vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); + desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID); - /* LUT size is only valid for Global and PF table types */ - switch (lut_size) { - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128: - break; - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512: - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - break; - case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K: - if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) { - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - break; - } - fallthrough; - default: - status = -EINVAL; - goto ice_aq_get_set_rss_lut_exit; - } + if (lut_type == ICE_LUT_GLOBAL) + glob_lut_idx = FIELD_PREP(ICE_AQC_LUT_GLOBAL_IDX, + params->global_lut_id); -ice_aq_get_set_rss_lut_send: - cmd_resp->flags = cpu_to_le16(flags); - status = ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL); + flags = lut_type | glob_lut_idx | ice_lut_size_to_flag(lut_size); + desc_params->flags = cpu_to_le16(flags); -ice_aq_get_set_rss_lut_exit: - return status; + return ice_aq_send_cmd(hw, &desc, lut, lut_size, NULL); } /** @@ -4008,12 +4047,10 @@ static int __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, struct ice_aqc_get_set_rss_keys *key, bool set) { - struct ice_aqc_get_set_rss_key *cmd_resp; + struct ice_aqc_get_set_rss_key *desc_params; u16 key_size = sizeof(*key); struct ice_aq_desc desc; - cmd_resp = &desc.params.get_set_rss_key; - if (set) { ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_key); desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); @@ -4021,10 +4058,8 @@ __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_key); } - cmd_resp->vsi_id = cpu_to_le16(((vsi_id << - ICE_AQC_GSET_RSS_KEY_VSI_ID_S) & - ICE_AQC_GSET_RSS_KEY_VSI_ID_M) | - ICE_AQC_GSET_RSS_KEY_VSI_VALID); + desc_params = &desc.params.get_set_rss_key; + desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID); return ice_aq_send_cmd(hw, &desc, key, key_size, NULL); } @@ -4222,6 +4257,53 @@ do_aq: } /** + * ice_aq_cfg_lan_txq + * @hw: pointer to the hardware structure + * @buf: buffer for command + * @buf_size: size of buffer in bytes + * @num_qs: number of queues being configured + * @oldport: origination lport + * @newport: destination lport + * @cd: pointer to command details structure or NULL + * + * Move/Configure LAN Tx queue (0x0C32) + * + * There is a better AQ command to use for moving nodes, so only coding + * this one for configuring the node. + */ +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + struct ice_sq_cd *cd) +{ + struct ice_aqc_cfg_txqs *cmd; + struct ice_aq_desc desc; + int status; + + cmd = &desc.params.cfg_txqs; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_cfg_txqs); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (!buf) + return -EINVAL; + + cmd->cmd_type = ICE_AQC_Q_CFG_TC_CHNG; + cmd->num_qs = num_qs; + cmd->port_num_chng = (oldport & ICE_AQC_Q_CFG_SRC_PRT_M); + cmd->port_num_chng |= (newport << ICE_AQC_Q_CFG_DST_PRT_S) & + ICE_AQC_Q_CFG_DST_PRT_M; + cmd->time_out = (5 << ICE_AQC_Q_CFG_TIMEOUT_S) & + ICE_AQC_Q_CFG_TIMEOUT_M; + cmd->blocked_cgds = 0; + + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (status) + ice_debug(hw, ICE_DBG_SCHED, "Failed to reconfigure nodes %d\n", + hw->adminq.sq_last_status); + return status; +} + +/** * ice_aq_add_rdma_qsets * @hw: pointer to the hardware structure * @num_qset_grps: Number of RDMA Qset groups @@ -4700,6 +4782,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, break; ice_free_sched_node(pi, node); q_ctx->q_handle = ICE_INVAL_Q_HANDLE; + q_ctx->q_teid = ICE_INVAL_TEID; } mutex_unlock(&pi->sched_lock); kfree(qg_list); diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 81961a7d6598..226b81f97a92 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -38,10 +38,9 @@ int ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res); int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res); -int -ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, - struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, - enum ice_adminq_opc opc, struct ice_sq_cd *cd); +int ice_aq_alloc_free_res(struct ice_hw *hw, + struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, + enum ice_adminq_opc opc); bool ice_is_sbq_supported(struct ice_hw *hw); struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw); int @@ -93,6 +92,7 @@ int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); +bool ice_is_pf_c827(struct ice_hw *hw); int ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd); @@ -186,6 +186,10 @@ int ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +int +ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf, + u16 buf_size, u16 num_qs, u8 oldport, u8 newport, + struct ice_sq_cd *cd); int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); void ice_replay_post(struct ice_hw *hw); void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 3eb01731e496..e1fbc6de452d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -70,6 +70,11 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); @@ -170,6 +175,11 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) if (mode == pf->dcbx_cap) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + qos_cfg = &pf->hw.port_info->qos_cfg; /* DSCP configuration is not DCBx negotiated */ @@ -261,6 +271,11 @@ static int ice_dcbnl_setpfc(struct net_device *netdev, struct ieee_pfc *pfc) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; @@ -323,6 +338,11 @@ static void ice_dcbnl_set_pfc_cfg(struct net_device *netdev, int prio, u8 set) if (prio >= ICE_MAX_USER_PRIORITY) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->pfc.pfccap = pf->hw.func_caps.common_cap.maxtc; @@ -379,6 +399,11 @@ static u8 ice_dcbnl_setstate(struct net_device *netdev, u8 state) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + /* Nothing to do */ if (!!state == test_bit(ICE_FLAG_DCB_ENA, pf->flags)) return ICE_DCB_NO_HW_CHG; @@ -451,6 +476,11 @@ ice_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, if (tc >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; /* prio_type, bwg_id and bw_pct per UP are not supported */ @@ -505,6 +535,11 @@ ice_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int pgid, u8 bw_pct) if (pgid >= ICE_MAX_TRAFFIC_CLASS) return; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; new_cfg->etscfg.tcbwtable[pgid] = bw_pct; @@ -725,6 +760,11 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + max_tc = pf->hw.func_caps.common_cap.maxtc; if (app->priority >= max_tc) { netdev_err(netdev, "TC %d out of range, max TC %d\n", @@ -836,6 +876,11 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; } + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return -EINVAL; + } + mutex_lock(&pf->tc_mutex); old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -937,6 +982,11 @@ static u8 ice_dcbnl_cee_set_all(struct net_device *netdev) !(pf->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return ICE_DCB_NO_HW_CHG; + if (pf->lag && pf->lag->bonded) { + netdev_err(netdev, "DCB changes not allowed when in a bond\n"); + return ICE_DCB_NO_HW_CHG; + } + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; mutex_lock(&pf->tc_mutex); diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index d71ed210f9c4..b27ec93638b6 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -30,7 +30,7 @@ static const struct ice_tunnel_type_scan tnls[] = { * Verifies various attributes of the package file, including length, format * version, and the requirement of at least one segment. */ -enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) +static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) { u32 seg_count; u32 i; @@ -118,7 +118,7 @@ static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) * * This helper function validates a buffer's header. */ -struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) +static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) { struct ice_buf_hdr *hdr; u16 section_count; @@ -1153,6 +1153,54 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw) } /** + * ice_aq_download_pkg + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer to transfer + * @buf_size: the size of the package buffer + * @last_buf: last buffer indicator + * @error_offset: returns error offset + * @error_info: returns error information + * @cd: pointer to command details structure or NULL + * + * Download Package (0x0C40) + */ +static int +ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd) +{ + struct ice_aqc_download_pkg *cmd; + struct ice_aq_desc desc; + int status; + + if (error_offset) + *error_offset = 0; + if (error_info) + *error_info = 0; + + cmd = &desc.params.download_pkg; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (last_buf) + cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + + status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + if (status == -EIO) { + /* Read error from buffer only when the FW returned an error */ + struct ice_aqc_download_pkg_resp *resp; + + resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** * ice_dwnld_cfg_bufs * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers @@ -1294,20 +1342,20 @@ static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, } /** - * ice_aq_download_pkg + * ice_aq_update_pkg * @hw: pointer to the hardware structure - * @pkg_buf: the package buffer to transfer - * @buf_size: the size of the package buffer + * @pkg_buf: the package cmd buffer + * @buf_size: the size of the package cmd buffer * @last_buf: last buffer indicator * @error_offset: returns error offset * @error_info: returns error information * @cd: pointer to command details structure or NULL * - * Download Package (0x0C40) + * Update Package (0x0C42) */ -int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd) +static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd) { struct ice_aqc_download_pkg *cmd; struct ice_aq_desc desc; @@ -1319,7 +1367,7 @@ int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, *error_info = 0; cmd = &desc.params.download_pkg; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg); desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); if (last_buf) @@ -1361,53 +1409,6 @@ int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, } /** - * ice_aq_update_pkg - * @hw: pointer to the hardware structure - * @pkg_buf: the package cmd buffer - * @buf_size: the size of the package cmd buffer - * @last_buf: last buffer indicator - * @error_offset: returns error offset - * @error_info: returns error information - * @cd: pointer to command details structure or NULL - * - * Update Package (0x0C42) - */ -static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd) -{ - struct ice_aqc_download_pkg *cmd; - struct ice_aq_desc desc; - int status; - - if (error_offset) - *error_offset = 0; - if (error_info) - *error_info = 0; - - cmd = &desc.params.download_pkg; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg); - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); - - if (last_buf) - cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; - - status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); - if (status == -EIO) { - /* Read error from buffer only when the FW returned an error */ - struct ice_aqc_download_pkg_resp *resp; - - resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; - if (error_offset) - *error_offset = le32_to_cpu(resp->error_offset); - if (error_info) - *error_info = le32_to_cpu(resp->error_info); - } - - return status; -} - -/** * ice_update_pkg_no_lock * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers @@ -1470,8 +1471,9 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) * success it returns a pointer to the segment header, otherwise it will * return NULL. */ -struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr) +static struct ice_generic_seg_hdr * +ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, + struct ice_pkg_hdr *pkg_hdr) { u32 i; diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h index 41acfe26df1c..abb5f32f2ef4 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.h +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -416,21 +416,13 @@ struct ice_pkg_enum { void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset); }; -int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, - u16 buf_size, bool last_buf, u32 *error_offset, - u32 *error_info, struct ice_sq_cd *cd); int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, struct ice_sq_cd *cd); void *ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size); -enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len); - struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw); -struct ice_generic_seg_hdr *ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, - struct ice_pkg_hdr *pkg_hdr); - int ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count); int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count); @@ -439,6 +431,4 @@ u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, u32 sect_type); -struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf); - #endif diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index ad0a007b7398..a655d499abfa 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -4,6 +4,7 @@ #include "ice.h" #include "ice_lib.h" #include "ice_eswitch.h" +#include "ice_eswitch_br.h" #include "ice_fltr.h" #include "ice_repr.h" #include "ice_devlink.h" @@ -83,10 +84,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) struct ice_vsi_vlan_ops *vlan_ops; bool rule_added = false; - vlan_ops = ice_get_compat_vsi_vlan_ops(ctrl_vsi); - if (vlan_ops->dis_stripping(ctrl_vsi)) - return -ENODEV; - ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); netif_addr_lock_bh(uplink_netdev); @@ -103,17 +100,28 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) rule_added = true; } + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + if (vlan_ops->dis_rx_filtering(uplink_vsi)) + goto err_dis_rx; + if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_uplink; if (ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_set_allow_override)) goto err_override_control; + if (ice_vsi_update_local_lb(uplink_vsi, true)) + goto err_override_local_lb; + return 0; +err_override_local_lb: + ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); err_override_control: ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); err_override_uplink: + vlan_ops->ena_rx_filtering(uplink_vsi); +err_dis_rx: if (rule_added) ice_clear_dflt_vsi(uplink_vsi); err_def_rx: @@ -306,6 +314,9 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) repr->src_vsi = vsi; repr->dst->u.port_info.port_id = vsi->vsi_num; + if (repr->br_port) + repr->br_port->vsi = vsi; + ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); if (ret) { ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); @@ -331,6 +342,9 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; + if (!vsi || !ice_is_switchdev_running(vsi->back)) + return NETDEV_TX_BUSY; + if (ice_is_reset_in_progress(vsi->back->state) || test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; @@ -378,9 +392,14 @@ static void ice_eswitch_release_env(struct ice_pf *pf) { struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi_vlan_ops *vlan_ops; + + vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi); + ice_vsi_update_local_lb(uplink_vsi, false); ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); + vlan_ops->ena_rx_filtering(uplink_vsi); ice_clear_dflt_vsi(uplink_vsi); ice_fltr_add_mac_and_broadcast(uplink_vsi, uplink_vsi->port_info->mac.perm_addr, @@ -455,16 +474,24 @@ static void ice_eswitch_napi_disable(struct ice_pf *pf) */ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) { - struct ice_vsi *ctrl_vsi; + struct ice_vsi *ctrl_vsi, *uplink_vsi; + + uplink_vsi = ice_get_main_vsi(pf); + if (!uplink_vsi) + return -ENODEV; + + if (netif_is_any_bridge_port(uplink_vsi->netdev)) { + dev_err(ice_pf_to_dev(pf), + "Uplink port cannot be a bridge port\n"); + return -EINVAL; + } pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info); if (!pf->switchdev.control_vsi) return -ENODEV; ctrl_vsi = pf->switchdev.control_vsi; - pf->switchdev.uplink_vsi = ice_get_main_vsi(pf); - if (!pf->switchdev.uplink_vsi) - goto err_vsi; + pf->switchdev.uplink_vsi = uplink_vsi; if (ice_eswitch_setup_env(pf)) goto err_vsi; @@ -480,10 +507,15 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf) if (ice_vsi_open(ctrl_vsi)) goto err_setup_reprs; + if (ice_eswitch_br_offloads_init(pf)) + goto err_br_offloads; + ice_eswitch_napi_enable(pf); return 0; +err_br_offloads: + ice_vsi_close(ctrl_vsi); err_setup_reprs: ice_repr_rem_from_all_vfs(pf); err_repr_add: @@ -502,8 +534,8 @@ static void ice_eswitch_disable_switchdev(struct ice_pf *pf) struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; ice_eswitch_napi_disable(pf); + ice_eswitch_br_offloads_deinit(pf); ice_eswitch_release_env(pf); - ice_rem_adv_rule_for_vsi(&pf->hw, ctrl_vsi->idx); ice_eswitch_release_reprs(pf, ctrl_vsi); ice_vsi_release(ctrl_vsi); ice_repr_rem_from_all_vfs(pf); @@ -538,6 +570,12 @@ ice_eswitch_mode_set(struct devlink *devlink, u16 mode, break; case DEVLINK_ESWITCH_MODE_SWITCHDEV: { + if (ice_is_adq_active(pf)) { + dev_err(ice_pf_to_dev(pf), "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root"); + NL_SET_ERR_MSG_MOD(extack, "Couldn't change eswitch mode to switchdev - ADQ is active. Delete ADQ configs and try again, e.g. tc qdisc del dev $PF root"); + return -EOPNOTSUPP; + } + dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev", pf->hw.pf_id); NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev"); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c new file mode 100644 index 000000000000..67bfd1f61cdd --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -0,0 +1,1346 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023, Intel Corporation. */ + +#include "ice.h" +#include "ice_eswitch_br.h" +#include "ice_repr.h" +#include "ice_switch.h" +#include "ice_vlan.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_trace.h" + +#define ICE_ESW_BRIDGE_UPDATE_INTERVAL msecs_to_jiffies(1000) + +static const struct rhashtable_params ice_fdb_ht_params = { + .key_offset = offsetof(struct ice_esw_br_fdb_entry, data), + .key_len = sizeof(struct ice_esw_br_fdb_data), + .head_offset = offsetof(struct ice_esw_br_fdb_entry, ht_node), + .automatic_shrinking = true, +}; + +static bool ice_eswitch_br_is_dev_valid(const struct net_device *dev) +{ + /* Accept only PF netdev, PRs and LAG */ + return ice_is_port_repr_netdev(dev) || netif_is_ice(dev) || + netif_is_lag_master(dev); +} + +static struct net_device * +ice_eswitch_br_get_uplink_from_lag(struct net_device *lag_dev) +{ + struct net_device *lower; + struct list_head *iter; + + netdev_for_each_lower_dev(lag_dev, lower, iter) { + if (netif_is_ice(lower)) + return lower; + } + + return NULL; +} + +static struct ice_esw_br_port * +ice_eswitch_br_netdev_to_port(struct net_device *dev) +{ + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + return repr->br_port; + } else if (netif_is_ice(dev) || netif_is_lag_master(dev)) { + struct net_device *ice_dev; + struct ice_pf *pf; + + if (netif_is_lag_master(dev)) + ice_dev = ice_eswitch_br_get_uplink_from_lag(dev); + else + ice_dev = dev; + + if (!ice_dev) + return NULL; + + pf = ice_netdev_to_pf(ice_dev); + + return pf->br_port; + } + + return NULL; +} + +static void +ice_eswitch_br_ingress_rule_setup(struct ice_adv_rule_info *rule_info, + u8 pf_id, u16 vf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = vf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_RX; + rule_info->sw_act.src = pf_id; + rule_info->priority = 5; +} + +static void +ice_eswitch_br_egress_rule_setup(struct ice_adv_rule_info *rule_info, + u16 pf_vsi_idx) +{ + rule_info->sw_act.vsi_handle = pf_vsi_idx; + rule_info->sw_act.flag |= ICE_FLTR_TX; + rule_info->flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; + rule_info->flags_info.act_valid = true; + rule_info->priority = 5; +} + +static int +ice_eswitch_br_rule_delete(struct ice_hw *hw, struct ice_rule_query_data *rule) +{ + int err; + + if (!rule) + return -EINVAL; + + err = ice_rem_adv_rule_by_id(hw, rule); + kfree(rule); + + return err; +} + +static u16 +ice_eswitch_br_get_lkups_cnt(u16 vid) +{ + return ice_eswitch_br_is_vid_valid(vid) ? 2 : 1; +} + +static void +ice_eswitch_br_add_vlan_lkup(struct ice_adv_lkup_elem *list, u16 vid) +{ + if (ice_eswitch_br_is_vid_valid(vid)) { + list[1].type = ICE_VLAN_OFOS; + list[1].h_u.vlan_hdr.vlan = cpu_to_be16(vid & VLAN_VID_MASK); + list[1].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF); + } +} + +static struct ice_rule_query_data * +ice_eswitch_br_fwd_rule_create(struct ice_hw *hw, int vsi_idx, int port_type, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + u16 lkups_cnt; + int err; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return ERR_PTR(-ENOMEM); + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) { + err = -ENOMEM; + goto err_list_alloc; + } + + switch (port_type) { + case ICE_ESWITCH_BR_UPLINK_PORT: + ice_eswitch_br_egress_rule_setup(&rule_info, vsi_idx); + break; + case ICE_ESWITCH_BR_VF_REPR_PORT: + ice_eswitch_br_ingress_rule_setup(&rule_info, hw->pf_id, + vsi_idx); + break; + default: + err = -EINVAL; + goto err_add_rule; + } + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.dst_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.dst_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.need_pass_l2 = true; + + rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); + + return ERR_PTR(err); +} + +static struct ice_rule_query_data * +ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx, + const unsigned char *mac, u16 vid) +{ + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data *rule; + struct ice_adv_lkup_elem *list; + int err = -ENOMEM; + u16 lkups_cnt; + + lkups_cnt = ice_eswitch_br_get_lkups_cnt(vid); + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + goto err_exit; + + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) + goto err_list_alloc; + + list[0].type = ICE_MAC_OFOS; + ether_addr_copy(list[0].h_u.eth_hdr.src_addr, mac); + eth_broadcast_addr(list[0].m_u.eth_hdr.src_addr); + + ice_eswitch_br_add_vlan_lkup(list, vid); + + rule_info.allow_pass_l2 = true; + rule_info.sw_act.vsi_handle = vsi_idx; + rule_info.sw_act.fltr_act = ICE_NOP; + rule_info.priority = 5; + + err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); + if (err) + goto err_add_rule; + + kfree(list); + + return rule; + +err_add_rule: + kfree(list); +err_list_alloc: + kfree(rule); +err_exit: + return ERR_PTR(err); +} + +static struct ice_esw_br_flow * +ice_eswitch_br_flow_create(struct device *dev, struct ice_hw *hw, int vsi_idx, + int port_type, const unsigned char *mac, u16 vid) +{ + struct ice_rule_query_data *fwd_rule, *guard_rule; + struct ice_esw_br_flow *flow; + int err; + + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + if (!flow) + return ERR_PTR(-ENOMEM); + + fwd_rule = ice_eswitch_br_fwd_rule_create(hw, vsi_idx, port_type, mac, + vid); + err = PTR_ERR_OR_ZERO(fwd_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress forward rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_fwd_rule; + } + + guard_rule = ice_eswitch_br_guard_rule_create(hw, vsi_idx, mac, vid); + err = PTR_ERR_OR_ZERO(guard_rule); + if (err) { + dev_err(dev, "Failed to create eswitch bridge %sgress guard rule, err: %d\n", + port_type == ICE_ESWITCH_BR_UPLINK_PORT ? "e" : "in", + err); + goto err_guard_rule; + } + + flow->fwd_rule = fwd_rule; + flow->guard_rule = guard_rule; + + return flow; + +err_guard_rule: + ice_eswitch_br_rule_delete(hw, fwd_rule); +err_fwd_rule: + kfree(flow); + + return ERR_PTR(err); +} + +static struct ice_esw_br_fdb_entry * +ice_eswitch_br_fdb_find(struct ice_esw_br *bridge, const unsigned char *mac, + u16 vid) +{ + struct ice_esw_br_fdb_data data = { + .vid = vid, + }; + + ether_addr_copy(data.addr, mac); + return rhashtable_lookup_fast(&bridge->fdb_ht, &data, + ice_fdb_ht_params); +} + +static void +ice_eswitch_br_flow_delete(struct ice_pf *pf, struct ice_esw_br_flow *flow) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->fwd_rule); + if (err) + dev_err(dev, "Failed to delete FDB forward rule, err: %d\n", + err); + + err = ice_eswitch_br_rule_delete(&pf->hw, flow->guard_rule); + if (err) + dev_err(dev, "Failed to delete FDB guard rule, err: %d\n", + err); + + kfree(flow); +} + +static struct ice_esw_br_vlan * +ice_esw_br_port_vlan_lookup(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) { + dev_info(dev, "Bridge port lookup failed (vsi=%u)\n", vsi_idx); + return ERR_PTR(-EINVAL); + } + + vlan = xa_load(&port->vlans, vid); + if (!vlan) { + dev_info(dev, "Bridge port vlan metadata lookup failed (vsi=%u)\n", + vsi_idx); + return ERR_PTR(-EINVAL); + } + + return vlan; +} + +static void +ice_eswitch_br_fdb_entry_delete(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *fdb_entry) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + + rhashtable_remove_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + list_del(&fdb_entry->list); + + ice_eswitch_br_flow_delete(pf, fdb_entry->flow); + + kfree(fdb_entry); +} + +static void +ice_eswitch_br_fdb_offload_notify(struct net_device *dev, + const unsigned char *mac, u16 vid, + unsigned long val) +{ + struct switchdev_notifier_fdb_info fdb_info = { + .addr = mac, + .vid = vid, + .offloaded = true, + }; + + call_switchdev_notifiers(val, dev, &fdb_info.info, NULL); +} + +static void +ice_eswitch_br_fdb_entry_notify_and_cleanup(struct ice_esw_br *bridge, + struct ice_esw_br_fdb_entry *entry) +{ + if (!(entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER)) + ice_eswitch_br_fdb_offload_notify(entry->dev, entry->data.addr, + entry->data.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + ice_eswitch_br_fdb_entry_delete(bridge, entry); +} + +static void +ice_eswitch_br_fdb_entry_find_and_delete(struct ice_esw_br *bridge, + const unsigned char *mac, u16 vid) +{ + struct ice_pf *pf = bridge->br_offloads->pf; + struct ice_esw_br_fdb_entry *fdb_entry; + struct device *dev = ice_pf_to_dev(pf); + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (!fdb_entry) { + dev_err(dev, "FDB entry with mac: %pM and vid: %u not found\n", + mac, vid); + return; + } + + trace_ice_eswitch_br_fdb_entry_find_and_delete(fdb_entry); + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); +} + +static void +ice_eswitch_br_fdb_entry_create(struct net_device *netdev, + struct ice_esw_br_port *br_port, + bool added_by_user, + const unsigned char *mac, u16 vid) +{ + struct ice_esw_br *bridge = br_port->bridge; + struct ice_pf *pf = bridge->br_offloads->pf; + struct device *dev = ice_pf_to_dev(pf); + struct ice_esw_br_fdb_entry *fdb_entry; + struct ice_esw_br_flow *flow; + struct ice_esw_br_vlan *vlan; + struct ice_hw *hw = &pf->hw; + unsigned long event; + int err; + + /* untagged filtering is not yet supported */ + if (!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING) && vid) + return; + + if ((bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) { + vlan = ice_esw_br_port_vlan_lookup(bridge, br_port->vsi_idx, + vid); + if (IS_ERR(vlan)) { + dev_err(dev, "Failed to find vlan lookup, err: %ld\n", + PTR_ERR(vlan)); + return; + } + } + + fdb_entry = ice_eswitch_br_fdb_find(bridge, mac, vid); + if (fdb_entry) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, fdb_entry); + + fdb_entry = kzalloc(sizeof(*fdb_entry), GFP_KERNEL); + if (!fdb_entry) { + err = -ENOMEM; + goto err_exit; + } + + flow = ice_eswitch_br_flow_create(dev, hw, br_port->vsi_idx, + br_port->type, mac, vid); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_add_flow; + } + + ether_addr_copy(fdb_entry->data.addr, mac); + fdb_entry->data.vid = vid; + fdb_entry->br_port = br_port; + fdb_entry->flow = flow; + fdb_entry->dev = netdev; + fdb_entry->last_use = jiffies; + event = SWITCHDEV_FDB_ADD_TO_BRIDGE; + + if (added_by_user) { + fdb_entry->flags |= ICE_ESWITCH_BR_FDB_ADDED_BY_USER; + event = SWITCHDEV_FDB_OFFLOADED; + } + + err = rhashtable_insert_fast(&bridge->fdb_ht, &fdb_entry->ht_node, + ice_fdb_ht_params); + if (err) + goto err_fdb_insert; + + list_add(&fdb_entry->list, &bridge->fdb_list); + trace_ice_eswitch_br_fdb_entry_create(fdb_entry); + + ice_eswitch_br_fdb_offload_notify(netdev, mac, vid, event); + + return; + +err_fdb_insert: + ice_eswitch_br_flow_delete(pf, flow); +err_add_flow: + kfree(fdb_entry); +err_exit: + dev_err(dev, "Failed to create fdb entry, err: %d\n", err); +} + +static void +ice_eswitch_br_fdb_work_dealloc(struct ice_esw_br_fdb_work *fdb_work) +{ + kfree(fdb_work->fdb_info.addr); + kfree(fdb_work); +} + +static void +ice_eswitch_br_fdb_event_work(struct work_struct *work) +{ + struct ice_esw_br_fdb_work *fdb_work = ice_work_to_fdb_work(work); + bool added_by_user = fdb_work->fdb_info.added_by_user; + const unsigned char *mac = fdb_work->fdb_info.addr; + u16 vid = fdb_work->fdb_info.vid; + struct ice_esw_br_port *br_port; + + rtnl_lock(); + + br_port = ice_eswitch_br_netdev_to_port(fdb_work->dev); + if (!br_port) + goto err_exit; + + switch (fdb_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + ice_eswitch_br_fdb_entry_create(fdb_work->dev, br_port, + added_by_user, mac, vid); + break; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + ice_eswitch_br_fdb_entry_find_and_delete(br_port->bridge, + mac, vid); + break; + default: + goto err_exit; + } + +err_exit: + rtnl_unlock(); + dev_put(fdb_work->dev); + ice_eswitch_br_fdb_work_dealloc(fdb_work); +} + +static struct ice_esw_br_fdb_work * +ice_eswitch_br_fdb_work_alloc(struct switchdev_notifier_fdb_info *fdb_info, + struct net_device *dev, + unsigned long event) +{ + struct ice_esw_br_fdb_work *work; + unsigned char *mac; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return ERR_PTR(-ENOMEM); + + INIT_WORK(&work->work, ice_eswitch_br_fdb_event_work); + memcpy(&work->fdb_info, fdb_info, sizeof(work->fdb_info)); + + mac = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!mac) { + kfree(work); + return ERR_PTR(-ENOMEM); + } + + ether_addr_copy(mac, fdb_info->addr); + work->fdb_info.addr = mac; + work->event = event; + work->dev = dev; + + return work; +} + +static int +ice_eswitch_br_switchdev_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_fdb_info *fdb_info; + struct switchdev_notifier_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct ice_esw_br_fdb_work *work; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, switchdev_nb); + extack = switchdev_notifier_info_to_extack(ptr); + + upper = netdev_master_upper_dev_get_rcu(dev); + if (!upper) + return NOTIFY_DONE; + + if (!netif_is_bridge_master(upper)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_is_dev_valid(dev)) + return NOTIFY_DONE; + + if (!ice_eswitch_br_netdev_to_port(dev)) + return NOTIFY_DONE; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = container_of(info, typeof(*fdb_info), info); + + work = ice_eswitch_br_fdb_work_alloc(fdb_info, dev, event); + if (IS_ERR(work)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init switchdev fdb work"); + return notifier_from_errno(PTR_ERR(work)); + } + dev_hold(dev); + + queue_work(br_offloads->wq, &work->work); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static void ice_eswitch_br_fdb_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_fdb_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); +} + +static void +ice_eswitch_br_vlan_filtering_set(struct ice_esw_br *bridge, bool enable) +{ + if (enable == !!(bridge->flags & ICE_ESWITCH_BR_VLAN_FILTERING)) + return; + + ice_eswitch_br_fdb_flush(bridge); + if (enable) + bridge->flags |= ICE_ESWITCH_BR_VLAN_FILTERING; + else + bridge->flags &= ~ICE_ESWITCH_BR_VLAN_FILTERING; +} + +static void +ice_eswitch_br_clear_pvid(struct ice_esw_br_port *port) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, port->pvid, 0); + struct ice_vsi_vlan_ops *vlan_ops; + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + + vlan_ops->del_vlan(port->vsi, &port_vlan); + vlan_ops->clear_port_vlan(port->vsi); + + ice_vf_vsi_disable_port_vlan(port->vsi); + + port->pvid = 0; +} + +static void +ice_eswitch_br_vlan_cleanup(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_esw_br *bridge = port->bridge; + + trace_ice_eswitch_br_vlan_cleanup(vlan); + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (vlan->vid == fdb_entry->data.vid) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + xa_erase(&port->vlans, vlan->vid); + if (port->pvid == vlan->vid) + ice_eswitch_br_clear_pvid(port); + kfree(vlan); +} + +static void ice_eswitch_br_port_vlans_flush(struct ice_esw_br_port *port) +{ + struct ice_esw_br_vlan *vlan; + unsigned long index; + + xa_for_each(&port->vlans, index, vlan) + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_set_pvid(struct ice_esw_br_port *port, + struct ice_esw_br_vlan *vlan) +{ + struct ice_vlan port_vlan = ICE_VLAN(ETH_P_8021Q, vlan->vid, 0); + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_vsi_vlan_ops *vlan_ops; + int err; + + if (port->pvid == vlan->vid || vlan->vid == 1) + return 0; + + /* Setting port vlan on uplink isn't supported by hw */ + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + return -EOPNOTSUPP; + + if (port->pvid) { + dev_info(dev, + "Port VLAN (vsi=%u, vid=%u) already exists on the port, remove it before adding new one\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + ice_vf_vsi_enable_port_vlan(port->vsi); + + vlan_ops = ice_get_compat_vsi_vlan_ops(port->vsi); + err = vlan_ops->set_port_vlan(port->vsi, &port_vlan); + if (err) + return err; + + err = vlan_ops->add_vlan(port->vsi, &port_vlan); + if (err) + return err; + + ice_eswitch_br_port_vlans_flush(port); + port->pvid = vlan->vid; + + return 0; +} + +static struct ice_esw_br_vlan * +ice_eswitch_br_vlan_create(u16 vid, u16 flags, struct ice_esw_br_port *port) +{ + struct device *dev = ice_pf_to_dev(port->vsi->back); + struct ice_esw_br_vlan *vlan; + int err; + + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return ERR_PTR(-ENOMEM); + + vlan->vid = vid; + vlan->flags = flags; + if ((flags & BRIDGE_VLAN_INFO_PVID) && + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + err = ice_eswitch_br_set_pvid(port, vlan); + if (err) + goto err_set_pvid; + } else if ((flags & BRIDGE_VLAN_INFO_PVID) || + (flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + dev_info(dev, "VLAN push and pop are supported only simultaneously\n"); + err = -EOPNOTSUPP; + goto err_set_pvid; + } + + err = xa_insert(&port->vlans, vlan->vid, vlan, GFP_KERNEL); + if (err) + goto err_insert; + + trace_ice_eswitch_br_vlan_create(vlan); + + return vlan; + +err_insert: + if (port->pvid) + ice_eswitch_br_clear_pvid(port); +err_set_pvid: + kfree(vlan); + return ERR_PTR(err); +} + +static int +ice_eswitch_br_port_vlan_add(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid, + u16 flags, struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return -EINVAL; + + if (port->pvid) { + dev_info(ice_pf_to_dev(port->vsi->back), + "Port VLAN (vsi=%u, vid=%d) exists on the port, remove it to add trunk VLANs\n", + port->vsi_idx, port->pvid); + return -EEXIST; + } + + vlan = xa_load(&port->vlans, vid); + if (vlan) { + if (vlan->flags == flags) + return 0; + + ice_eswitch_br_vlan_cleanup(port, vlan); + } + + vlan = ice_eswitch_br_vlan_create(vid, flags, port); + if (IS_ERR(vlan)) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to create VLAN entry, vid: %u, vsi: %u", + vid, vsi_idx); + return PTR_ERR(vlan); + } + + return 0; +} + +static void +ice_eswitch_br_port_vlan_del(struct ice_esw_br *bridge, u16 vsi_idx, u16 vid) +{ + struct ice_esw_br_port *port; + struct ice_esw_br_vlan *vlan; + + port = xa_load(&bridge->ports, vsi_idx); + if (!port) + return; + + vlan = xa_load(&port->vlans, vid); + if (!vlan) + return; + + ice_eswitch_br_vlan_cleanup(port, vlan); +} + +static int +ice_eswitch_br_port_obj_add(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + int err; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + err = ice_eswitch_br_port_vlan_add(br_port->bridge, + br_port->vsi_idx, vlan->vid, + vlan->flags, extack); + return err; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_del(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + struct switchdev_obj_port_vlan *vlan; + + if (!br_port) + return -EINVAL; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + ice_eswitch_br_port_vlan_del(br_port->bridge, br_port->vsi_idx, + vlan->vid); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_port_obj_attr_set(struct net_device *netdev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(netdev); + + if (!br_port) + return -EINVAL; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + ice_eswitch_br_vlan_filtering_set(br_port->bridge, + attr->u.vlan_filtering); + return 0; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + br_port->bridge->ageing_time = + clock_t_to_jiffies(attr->u.ageing_time); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +ice_eswitch_br_event_blocking(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_add); + break; + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_del); + break; + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + ice_eswitch_br_is_dev_valid, + ice_eswitch_br_port_obj_attr_set); + break; + default: + err = 0; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_port_deinit(struct ice_esw_br *bridge, + struct ice_esw_br_port *br_port) +{ + struct ice_esw_br_fdb_entry *fdb_entry, *tmp; + struct ice_vsi *vsi = br_port->vsi; + + list_for_each_entry_safe(fdb_entry, tmp, &bridge->fdb_list, list) { + if (br_port == fdb_entry->br_port) + ice_eswitch_br_fdb_entry_delete(bridge, fdb_entry); + } + + if (br_port->type == ICE_ESWITCH_BR_UPLINK_PORT && vsi->back) + vsi->back->br_port = NULL; + else if (vsi->vf && vsi->vf->repr) + vsi->vf->repr->br_port = NULL; + + xa_erase(&bridge->ports, br_port->vsi_idx); + ice_eswitch_br_port_vlans_flush(br_port); + kfree(br_port); +} + +static struct ice_esw_br_port * +ice_eswitch_br_port_init(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *br_port; + + br_port = kzalloc(sizeof(*br_port), GFP_KERNEL); + if (!br_port) + return ERR_PTR(-ENOMEM); + + xa_init(&br_port->vlans); + + br_port->bridge = bridge; + + return br_port; +} + +static int +ice_eswitch_br_vf_repr_port_init(struct ice_esw_br *bridge, + struct ice_repr *repr) +{ + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = repr->src_vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_VF_REPR_PORT; + repr->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static int +ice_eswitch_br_uplink_port_init(struct ice_esw_br *bridge, struct ice_pf *pf) +{ + struct ice_vsi *vsi = pf->switchdev.uplink_vsi; + struct ice_esw_br_port *br_port; + int err; + + br_port = ice_eswitch_br_port_init(bridge); + if (IS_ERR(br_port)) + return PTR_ERR(br_port); + + br_port->vsi = vsi; + br_port->vsi_idx = br_port->vsi->idx; + br_port->type = ICE_ESWITCH_BR_UPLINK_PORT; + pf->br_port = br_port; + + err = xa_insert(&bridge->ports, br_port->vsi_idx, br_port, GFP_KERNEL); + if (err) { + ice_eswitch_br_port_deinit(bridge, br_port); + return err; + } + + return 0; +} + +static void +ice_eswitch_br_ports_flush(struct ice_esw_br *bridge) +{ + struct ice_esw_br_port *port; + unsigned long i; + + xa_for_each(&bridge->ports, i, port) + ice_eswitch_br_port_deinit(bridge, port); +} + +static void +ice_eswitch_br_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + if (!bridge) + return; + + /* Cleanup all the ports that were added asynchronously + * through NETDEV_CHANGEUPPER event. + */ + ice_eswitch_br_ports_flush(bridge); + WARN_ON(!xa_empty(&bridge->ports)); + xa_destroy(&bridge->ports); + rhashtable_destroy(&bridge->fdb_ht); + + br_offloads->bridge = NULL; + kfree(bridge); +} + +static struct ice_esw_br * +ice_eswitch_br_init(struct ice_esw_br_offloads *br_offloads, int ifindex) +{ + struct ice_esw_br *bridge; + int err; + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return ERR_PTR(-ENOMEM); + + err = rhashtable_init(&bridge->fdb_ht, &ice_fdb_ht_params); + if (err) { + kfree(bridge); + return ERR_PTR(err); + } + + INIT_LIST_HEAD(&bridge->fdb_list); + bridge->br_offloads = br_offloads; + bridge->ifindex = ifindex; + bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME); + xa_init(&bridge->ports); + br_offloads->bridge = bridge; + + return bridge; +} + +static struct ice_esw_br * +ice_eswitch_br_get(struct ice_esw_br_offloads *br_offloads, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + + if (bridge) { + if (bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Only one bridge is supported per eswitch"); + return ERR_PTR(-EOPNOTSUPP); + } + return bridge; + } + + /* Create the bridge if it doesn't exist yet */ + bridge = ice_eswitch_br_init(br_offloads, ifindex); + if (IS_ERR(bridge)) + NL_SET_ERR_MSG_MOD(extack, "Failed to init the bridge"); + + return bridge; +} + +static void +ice_eswitch_br_verify_deinit(struct ice_esw_br_offloads *br_offloads, + struct ice_esw_br *bridge) +{ + /* Remove the bridge if it exists and there are no ports left */ + if (!bridge || !xa_empty(&bridge->ports)) + return; + + ice_eswitch_br_deinit(br_offloads, bridge); +} + +static int +ice_eswitch_br_port_unlink(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br_port *br_port = ice_eswitch_br_netdev_to_port(dev); + struct ice_esw_br *bridge; + + if (!br_port) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is not attached to any bridge"); + return -EINVAL; + } + + if (br_port->bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "Port representor is attached to another bridge"); + return -EINVAL; + } + + bridge = br_port->bridge; + + trace_ice_eswitch_br_port_unlink(br_port); + ice_eswitch_br_port_deinit(br_port->bridge, br_port); + ice_eswitch_br_verify_deinit(br_offloads, bridge); + + return 0; +} + +static int +ice_eswitch_br_port_link(struct ice_esw_br_offloads *br_offloads, + struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) +{ + struct ice_esw_br *bridge; + int err; + + if (ice_eswitch_br_netdev_to_port(dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Port is already attached to the bridge"); + return -EINVAL; + } + + bridge = ice_eswitch_br_get(br_offloads, ifindex, extack); + if (IS_ERR(bridge)) + return PTR_ERR(bridge); + + if (ice_is_port_repr_netdev(dev)) { + struct ice_repr *repr = ice_netdev_to_repr(dev); + + err = ice_eswitch_br_vf_repr_port_init(bridge, repr); + trace_ice_eswitch_br_port_link(repr->br_port); + } else { + struct net_device *ice_dev; + struct ice_pf *pf; + + if (netif_is_lag_master(dev)) + ice_dev = ice_eswitch_br_get_uplink_from_lag(dev); + else + ice_dev = dev; + + if (!ice_dev) + return 0; + + pf = ice_netdev_to_pf(ice_dev); + + err = ice_eswitch_br_uplink_port_init(bridge, pf); + trace_ice_eswitch_br_port_link(pf->br_port); + } + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to init bridge port"); + goto err_port_init; + } + + return 0; + +err_port_init: + ice_eswitch_br_verify_deinit(br_offloads, bridge); + return err; +} + +static int +ice_eswitch_br_port_changeupper(struct notifier_block *nb, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_esw_br_offloads *br_offloads; + struct netlink_ext_ack *extack; + struct net_device *upper; + + br_offloads = ice_nb_to_br_offloads(nb, netdev_nb); + + if (!ice_eswitch_br_is_dev_valid(dev)) + return 0; + + upper = info->upper_dev; + if (!netif_is_bridge_master(upper)) + return 0; + + extack = netdev_notifier_info_to_extack(&info->info); + + if (info->linking) + return ice_eswitch_br_port_link(br_offloads, dev, + upper->ifindex, extack); + else + return ice_eswitch_br_port_unlink(br_offloads, dev, + upper->ifindex, extack); +} + +static int +ice_eswitch_br_port_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + int err = 0; + + switch (event) { + case NETDEV_CHANGEUPPER: + err = ice_eswitch_br_port_changeupper(nb, ptr); + break; + } + + return notifier_from_errno(err); +} + +static void +ice_eswitch_br_offloads_dealloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads = pf->switchdev.br_offloads; + + ASSERT_RTNL(); + + if (!br_offloads) + return; + + ice_eswitch_br_deinit(br_offloads, br_offloads->bridge); + + pf->switchdev.br_offloads = NULL; + kfree(br_offloads); +} + +static struct ice_esw_br_offloads * +ice_eswitch_br_offloads_alloc(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + ASSERT_RTNL(); + + if (pf->switchdev.br_offloads) + return ERR_PTR(-EEXIST); + + br_offloads = kzalloc(sizeof(*br_offloads), GFP_KERNEL); + if (!br_offloads) + return ERR_PTR(-ENOMEM); + + pf->switchdev.br_offloads = br_offloads; + br_offloads->pf = pf; + + return br_offloads; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = pf->switchdev.br_offloads; + if (!br_offloads) + return; + + cancel_delayed_work_sync(&br_offloads->update_work); + unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + unregister_switchdev_notifier(&br_offloads->switchdev_nb); + destroy_workqueue(br_offloads->wq); + /* Although notifier block is unregistered just before, + * so we don't get any new events, some events might be + * already in progress. Hold the rtnl lock and wait for + * them to finished. + */ + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); +} + +static void ice_eswitch_br_update(struct ice_esw_br_offloads *br_offloads) +{ + struct ice_esw_br *bridge = br_offloads->bridge; + struct ice_esw_br_fdb_entry *entry, *tmp; + + if (!bridge) + return; + + rtnl_lock(); + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { + if (entry->flags & ICE_ESWITCH_BR_FDB_ADDED_BY_USER) + continue; + + if (time_is_after_eq_jiffies(entry->last_use + + bridge->ageing_time)) + continue; + + ice_eswitch_br_fdb_entry_notify_and_cleanup(bridge, entry); + } + rtnl_unlock(); +} + +static void ice_eswitch_br_update_work(struct work_struct *work) +{ + struct ice_esw_br_offloads *br_offloads; + + br_offloads = ice_work_to_br_offloads(work); + + ice_eswitch_br_update(br_offloads); + + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); +} + +int +ice_eswitch_br_offloads_init(struct ice_pf *pf) +{ + struct ice_esw_br_offloads *br_offloads; + struct device *dev = ice_pf_to_dev(pf); + int err; + + rtnl_lock(); + br_offloads = ice_eswitch_br_offloads_alloc(pf); + rtnl_unlock(); + if (IS_ERR(br_offloads)) { + dev_err(dev, "Failed to init eswitch bridge\n"); + return PTR_ERR(br_offloads); + } + + br_offloads->wq = alloc_ordered_workqueue("ice_bridge_wq", 0); + if (!br_offloads->wq) { + err = -ENOMEM; + dev_err(dev, "Failed to allocate bridge workqueue\n"); + goto err_alloc_wq; + } + + br_offloads->switchdev_nb.notifier_call = + ice_eswitch_br_switchdev_event; + err = register_switchdev_notifier(&br_offloads->switchdev_nb); + if (err) { + dev_err(dev, + "Failed to register switchdev notifier\n"); + goto err_reg_switchdev_nb; + } + + br_offloads->switchdev_blk.notifier_call = + ice_eswitch_br_event_blocking; + err = register_switchdev_blocking_notifier(&br_offloads->switchdev_blk); + if (err) { + dev_err(dev, + "Failed to register bridge blocking switchdev notifier\n"); + goto err_reg_switchdev_blk; + } + + br_offloads->netdev_nb.notifier_call = ice_eswitch_br_port_event; + err = register_netdevice_notifier(&br_offloads->netdev_nb); + if (err) { + dev_err(dev, + "Failed to register bridge port event notifier\n"); + goto err_reg_netdev_nb; + } + + INIT_DELAYED_WORK(&br_offloads->update_work, + ice_eswitch_br_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + ICE_ESW_BRIDGE_UPDATE_INTERVAL); + + return 0; + +err_reg_netdev_nb: + unregister_switchdev_blocking_notifier(&br_offloads->switchdev_blk); +err_reg_switchdev_blk: + unregister_switchdev_notifier(&br_offloads->switchdev_nb); +err_reg_switchdev_nb: + destroy_workqueue(br_offloads->wq); +err_alloc_wq: + rtnl_lock(); + ice_eswitch_br_offloads_dealloc(pf); + rtnl_unlock(); + + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.h b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h new file mode 100644 index 000000000000..85a8fadb2928 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023, Intel Corporation. */ + +#ifndef _ICE_ESWITCH_BR_H_ +#define _ICE_ESWITCH_BR_H_ + +#include <linux/rhashtable.h> +#include <linux/workqueue.h> + +struct ice_esw_br_fdb_data { + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +struct ice_esw_br_flow { + struct ice_rule_query_data *fwd_rule; + struct ice_rule_query_data *guard_rule; +}; + +enum { + ICE_ESWITCH_BR_FDB_ADDED_BY_USER = BIT(0), +}; + +struct ice_esw_br_fdb_entry { + struct ice_esw_br_fdb_data data; + struct rhash_head ht_node; + struct list_head list; + + int flags; + + struct net_device *dev; + struct ice_esw_br_port *br_port; + struct ice_esw_br_flow *flow; + + unsigned long last_use; +}; + +enum ice_esw_br_port_type { + ICE_ESWITCH_BR_UPLINK_PORT = 0, + ICE_ESWITCH_BR_VF_REPR_PORT = 1, +}; + +struct ice_esw_br_port { + struct ice_esw_br *bridge; + struct ice_vsi *vsi; + enum ice_esw_br_port_type type; + u16 vsi_idx; + u16 pvid; + struct xarray vlans; +}; + +enum { + ICE_ESWITCH_BR_VLAN_FILTERING = BIT(0), +}; + +struct ice_esw_br { + struct ice_esw_br_offloads *br_offloads; + struct xarray ports; + + struct rhashtable fdb_ht; + struct list_head fdb_list; + + int ifindex; + u32 flags; + unsigned long ageing_time; +}; + +struct ice_esw_br_offloads { + struct ice_pf *pf; + struct ice_esw_br *bridge; + struct notifier_block netdev_nb; + struct notifier_block switchdev_blk; + struct notifier_block switchdev_nb; + + struct workqueue_struct *wq; + struct delayed_work update_work; +}; + +struct ice_esw_br_fdb_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct net_device *dev; + unsigned long event; +}; + +struct ice_esw_br_vlan { + u16 vid; + u16 flags; +}; + +#define ice_nb_to_br_offloads(nb, nb_name) \ + container_of(nb, \ + struct ice_esw_br_offloads, \ + nb_name) + +#define ice_work_to_br_offloads(w) \ + container_of(w, \ + struct ice_esw_br_offloads, \ + update_work.work) + +#define ice_work_to_fdb_work(w) \ + container_of(w, \ + struct ice_esw_br_fdb_work, \ + work) + +static inline bool ice_eswitch_br_is_vid_valid(u16 vid) +{ + /* In trunk VLAN mode, for untagged traffic the bridge sends requests + * to offload VLAN 1 with pvid and untagged flags set. Since these + * flags are not supported, add a MAC filter instead. + */ + return vid > 1; +} + +void +ice_eswitch_br_offloads_deinit(struct ice_pf *pf); +int +ice_eswitch_br_offloads_init(struct ice_pf *pf); + +#endif /* _ICE_ESWITCH_BR_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 8d5cbbd0b3d5..ad4d4702129f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2681,8 +2681,13 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, ring->rx_max_pending = ICE_MAX_NUM_DESC; ring->tx_max_pending = ICE_MAX_NUM_DESC; - ring->rx_pending = vsi->rx_rings[0]->count; - ring->tx_pending = vsi->tx_rings[0]->count; + if (vsi->tx_rings && vsi->rx_rings) { + ring->rx_pending = vsi->rx_rings[0]->count; + ring->tx_pending = vsi->tx_rings[0]->count; + } else { + ring->rx_pending = 0; + ring->tx_pending = 0; + } /* Rx mini and jumbo rings are not supported */ ring->rx_mini_max_pending = 0; @@ -2716,6 +2721,10 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, return -EINVAL; } + /* Return if there is no rings (device is reloading) */ + if (!vsi->tx_rings || !vsi->rx_rings) + return -EBUSY; + new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE); if (new_tx_cnt != ring->tx_pending) netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index ead6d50fc0ad..8c6e13f87b7d 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1281,16 +1281,21 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, ICE_FLOW_FLD_OFF_INVAL); } - /* add filter for outer headers */ fltr_idx = ice_ethtool_flow_to_fltr(fsp->flow_type & ~FLOW_EXT); + + assign_bit(fltr_idx, hw->fdir_perfect_fltr, perfect_filter); + + /* add filter for outer headers */ ret = ice_fdir_set_hw_fltr_rule(pf, seg, fltr_idx, ICE_FD_HW_SEG_NON_TUN); - if (ret == -EEXIST) - /* Rule already exists, free memory and continue */ - devm_kfree(dev, seg); - else if (ret) + if (ret == -EEXIST) { + /* Rule already exists, free memory and count as success */ + ret = 0; + goto err_exit; + } else if (ret) { /* could not write filter, free memory */ goto err_exit; + } /* make tunneled filter HW entries if possible */ memcpy(&tun_seg[1], seg, sizeof(*seg)); @@ -1305,18 +1310,13 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, devm_kfree(dev, tun_seg); } - if (perfect_filter) - set_bit(fltr_idx, hw->fdir_perfect_fltr); - else - clear_bit(fltr_idx, hw->fdir_perfect_fltr); - return ret; err_exit: devm_kfree(dev, tun_seg); devm_kfree(dev, seg); - return -EOPNOTSUPP; + return ret; } /** @@ -1914,7 +1914,9 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) input->comp_report = ICE_FXD_FLTR_QW0_COMP_REPORT_SW_FAIL; /* input struct is added to the HW filter list */ - ice_fdir_update_list_entry(pf, input, fsp->location); + ret = ice_fdir_update_list_entry(pf, input, fsp->location); + if (ret) + goto release_lock; ret = ice_fdir_write_all_fltr(pf, input, true); if (ret) diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 3dc5662d62a6..319a2d6fe26c 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -293,16 +293,17 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; + struct ice_aq_desc *desc; u32 completion_offset; int err; - memset(&event, 0, sizeof(event)); - dev_dbg(dev, "Writing block of %u bytes for module 0x%02x at offset %u\n", block_size, module, offset); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write); + err = ice_aq_update_nvm(hw, module, offset, block_size, block, last_cmd, 0, NULL); if (err) { @@ -319,7 +320,7 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, * is conservative and is intended to prevent failure to update when * firmware is slow to respond. */ - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, 15 * HZ, &event); + err = ice_aq_wait_for_event(pf, &task, 15 * HZ); if (err) { dev_err(dev, "Timed out while trying to flash module 0x%02x with block of size %u at offset %u, err %d\n", module, block_size, offset, err); @@ -327,11 +328,12 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, return -EIO; } - completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); - completion_retval = le16_to_cpu(event.desc.retval); + desc = &task.event.desc; + completion_module = le16_to_cpu(desc->params.nvm.module_typeid); + completion_retval = le16_to_cpu(desc->retval); - completion_offset = le16_to_cpu(event.desc.params.nvm.offset_low); - completion_offset |= event.desc.params.nvm.offset_high << 16; + completion_offset = le16_to_cpu(desc->params.nvm.offset_low); + completion_offset |= desc->params.nvm.offset_high << 16; if (completion_module != module) { dev_err(dev, "Unexpected module_typeid in write completion: got 0x%x, expected 0x%x\n", @@ -363,8 +365,8 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, */ if (reset_level && last_cmd && module == ICE_SR_1ST_NVM_BANK_PTR) { if (hw->dev_caps.common_cap.pcie_reset_avoidance) { - *reset_level = (event.desc.params.nvm.cmd_flags & - ICE_AQC_NVM_RESET_LVL_M); + *reset_level = desc->params.nvm.cmd_flags & + ICE_AQC_NVM_RESET_LVL_M; dev_dbg(dev, "Firmware reported required reset level as %u\n", *reset_level); } else { @@ -479,19 +481,20 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; + struct ice_aq_desc *desc; struct devlink *devlink; int err; dev_dbg(dev, "Beginning erase of flash component '%s', module 0x%02x\n", component, module); - memset(&event, 0, sizeof(event)); - devlink = priv_to_devlink(pf); devlink_flash_update_timeout_notify(devlink, "Erasing", component, ICE_FW_ERASE_TIMEOUT); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_erase); + err = ice_aq_erase_nvm(hw, module, NULL); if (err) { dev_err(dev, "Failed to erase %s (module 0x%02x), err %d aq_err %s\n", @@ -502,7 +505,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, goto out_notify_devlink; } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_erase, ICE_FW_ERASE_TIMEOUT * HZ, &event); + err = ice_aq_wait_for_event(pf, &task, ICE_FW_ERASE_TIMEOUT * HZ); if (err) { dev_err(dev, "Timed out waiting for firmware to respond with erase completion for %s (module 0x%02x), err %d\n", component, module, err); @@ -510,8 +513,9 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, goto out_notify_devlink; } - completion_module = le16_to_cpu(event.desc.params.nvm.module_typeid); - completion_retval = le16_to_cpu(event.desc.retval); + desc = &task.event.desc; + completion_module = le16_to_cpu(desc->params.nvm.module_typeid); + completion_retval = le16_to_cpu(desc->retval); if (completion_module != module) { dev_err(dev, "Unexpected module_typeid in erase completion for %s: got 0x%x, expected 0x%x\n", @@ -560,13 +564,13 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, u8 *emp_reset_available, struct netlink_ext_ack *extack) { struct device *dev = ice_pf_to_dev(pf); - struct ice_rq_event_info event; + struct ice_aq_task task = {}; struct ice_hw *hw = &pf->hw; u16 completion_retval; u8 response_flags; int err; - memset(&event, 0, sizeof(event)); + ice_aq_prep_for_event(pf, &task, ice_aqc_opc_nvm_write_activate); err = ice_nvm_write_activate(hw, activate_flags, &response_flags); if (err) { @@ -592,8 +596,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, } } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ, - &event); + err = ice_aq_wait_for_event(pf, &task, 30 * HZ); if (err) { dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n", err); @@ -601,7 +604,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, return err; } - completion_retval = le16_to_cpu(event.desc.retval); + completion_retval = le16_to_cpu(task.event.desc.retval); if (completion_retval) { dev_err(dev, "Firmware failed to switch active flash banks aq_err %s\n", ice_aq_str((enum ice_aq_err)completion_retval)); diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index a92dc9a16035..531cc2194741 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -335,6 +335,8 @@ #define VP_MDET_TX_TCLAN_VALID_M BIT(0) #define VP_MDET_TX_TDPU(_VF) (0x00040000 + ((_VF) * 4)) #define VP_MDET_TX_TDPU_VALID_M BIT(0) +#define GL_MNG_FWSM 0x000B6134 +#define GL_MNG_FWSM_FW_LOADING_M BIT(30) #define GLNVM_FLA 0x000B6108 #define GLNVM_FLA_LOCKED_M BIT(6) #define GLNVM_GENS 0x000B6100 @@ -489,7 +491,6 @@ #define VSIQF_FD_CNT_FD_BCNT_M ICE_M(0x3FFF, 16) #define VSIQF_FD_SIZE(_VSI) (0x00462000 + ((_VSI) * 4)) #define VSIQF_HKEY_MAX_INDEX 12 -#define VSIQF_HLUT_MAX_INDEX 15 #define PFPM_APM 0x000B8080 #define PFPM_APM_APME_M BIT(0) #define PFPM_WUFC 0x0009DC00 diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 5a7753bda324..4f39863b5537 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -4,8 +4,24 @@ /* Link Aggregation code */ #include "ice.h" +#include "ice_lib.h" #include "ice_lag.h" +#define ICE_LAG_RES_SHARED BIT(14) +#define ICE_LAG_RES_VALID BIT(15) + +#define LACP_TRAIN_PKT_LEN 16 +static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, + 0x88, 0x09, 0, 0 }; + +#define ICE_RECIPE_LEN 64 +static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = { + 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; + /** * ice_lag_set_primary - set PF LAG state as Primary * @lag: LAG info struct @@ -47,16 +63,219 @@ static void ice_lag_set_backup(struct ice_lag *lag) } /** + * netif_is_same_ice - determine if netdev is on the same ice NIC as local PF + * @pf: local PF struct + * @netdev: netdev we are evaluating + */ +static bool netif_is_same_ice(struct ice_pf *pf, struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *test_pf; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return false; + + np = netdev_priv(netdev); + if (!np) + return false; + + vsi = np->vsi; + if (!vsi) + return false; + + test_pf = vsi->back; + if (!test_pf) + return false; + + if (pf->pdev->bus != test_pf->pdev->bus || + pf->pdev->slot != test_pf->pdev->slot) + return false; + + return true; +} + +/** + * ice_netdev_to_lag - return pointer to associated lag struct from netdev + * @netdev: pointer to net_device struct to query + */ +static struct ice_lag *ice_netdev_to_lag(struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_vsi *vsi; + + if (!netif_is_ice(netdev)) + return NULL; + + np = netdev_priv(netdev); + if (!np) + return NULL; + + vsi = np->vsi; + if (!vsi) + return NULL; + + return vsi->back->lag; +} + +/** + * ice_lag_find_hw_by_lport - return an hw struct from bond members lport + * @lag: lag struct + * @lport: lport value to search for + */ +static struct ice_hw * +ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport) +{ + struct ice_lag_netdev_list *entry; + struct net_device *tmp_netdev; + struct ice_netdev_priv *np; + struct ice_hw *hw; + + list_for_each_entry(entry, lag->netdev_head, node) { + tmp_netdev = entry->netdev; + if (!tmp_netdev || !netif_is_ice(tmp_netdev)) + continue; + + np = netdev_priv(tmp_netdev); + if (!np || !np->vsi) + continue; + + hw = &np->vsi->back->hw; + if (hw->port_info->lport == lport) + return hw; + } + + return NULL; +} + +/** + * ice_lag_find_primary - returns pointer to primary interfaces lag struct + * @lag: local interfaces lag struct + */ +static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag) +{ + struct ice_lag *primary_lag = NULL; + struct list_head *tmp; + + list_for_each(tmp, lag->netdev_head) { + struct ice_lag_netdev_list *entry; + struct ice_lag *tmp_lag; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + tmp_lag = ice_netdev_to_lag(entry->netdev); + if (tmp_lag && tmp_lag->primary) { + primary_lag = tmp_lag; + break; + } + } + + return primary_lag; +} + +/** + * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG + * @lag: lag struct for local interface + * @add: boolean on whether we are adding filters + */ +static int +ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule; + u16 s_rule_sz, vsi_num; + struct ice_hw *hw; + u32 act, opc; + u8 *eth_hdr; + int err; + + hw = &lag->pf->hw; + vsi_num = ice_get_hw_vsi_num(hw, 0); + + s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule); + s_rule = kzalloc(s_rule_sz, GFP_KERNEL); + if (!s_rule) { + dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG default VSI\n"); + return -ENOMEM; + } + + if (add) { + eth_hdr = s_rule->hdr_data; + ice_fill_eth_hdr(eth_hdr); + + act = (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) & + ICE_SINGLE_ACT_VSI_ID_M; + act |= ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE; + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(lag->pf_recipe); + s_rule->src = cpu_to_le16(hw->port_info->lport); + s_rule->act = cpu_to_le32(act); + s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN); + opc = ice_aqc_opc_add_sw_rules; + } else { + s_rule->index = cpu_to_le16(lag->pf_rule_id); + opc = ice_aqc_opc_remove_sw_rules; + } + + err = ice_aq_sw_rules(&lag->pf->hw, s_rule, s_rule_sz, 1, opc, NULL); + if (err) + goto dflt_fltr_free; + + if (add) + lag->pf_rule_id = le16_to_cpu(s_rule->index); + else + lag->pf_rule_id = 0; + +dflt_fltr_free: + kfree(s_rule); + return err; +} + +/** + * ice_lag_cfg_pf_fltrs - set filters up for new active port + * @lag: local interfaces lag struct + * @ptr: opaque data containing notifier event + */ +static void +ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct net_device *event_netdev; + struct device *dev; + + event_netdev = netdev_notifier_info_to_dev(ptr); + /* not for this netdev */ + if (event_netdev != lag->netdev) + return; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + dev = ice_pf_to_dev(lag->pf); + + /* interface not active - remove old default VSI rule */ + if (bonding_info->slave.state && lag->pf_rule_id) { + if (ice_lag_cfg_dflt_fltr(lag, false)) + dev_err(dev, "Error removing old default VSI filter\n"); + return; + } + + /* interface becoming active - add new default VSI rule */ + if (!bonding_info->slave.state && !lag->pf_rule_id) + if (ice_lag_cfg_dflt_fltr(lag, true)) + dev_err(dev, "Error adding new default VSI filter\n"); +} + +/** * ice_display_lag_info - print LAG info * @lag: LAG info struct */ static void ice_display_lag_info(struct ice_lag *lag) { - const char *name, *peer, *upper, *role, *bonded, *primary; + const char *name, *upper, *role, *bonded, *primary; struct device *dev = &lag->pf->pdev->dev; name = lag->netdev ? netdev_name(lag->netdev) : "unset"; - peer = lag->peer_netdev ? netdev_name(lag->peer_netdev) : "unset"; upper = lag->upper_netdev ? netdev_name(lag->upper_netdev) : "unset"; primary = lag->primary ? "TRUE" : "FALSE"; bonded = lag->bonded ? "BONDED" : "UNBONDED"; @@ -78,8 +297,410 @@ static void ice_display_lag_info(struct ice_lag *lag) role = "ERROR"; } - dev_dbg(dev, "%s %s, peer:%s, upper:%s, role:%s, primary:%s\n", name, - bonded, peer, upper, role, primary); + dev_dbg(dev, "%s %s, upper:%s, role:%s, primary:%s\n", name, bonded, + upper, role, primary); +} + +/** + * ice_lag_qbuf_recfg - generate a buffer of queues for a reconfigure command + * @hw: HW struct that contains the queue contexts + * @qbuf: pointer to buffer to populate + * @vsi_num: index of the VSI in PF space + * @numq: number of queues to search for + * @tc: traffic class that contains the queues + * + * function returns the number of valid queues in buffer + */ +static u16 +ice_lag_qbuf_recfg(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *qbuf, + u16 vsi_num, u16 numq, u8 tc) +{ + struct ice_q_ctx *q_ctx; + u16 qid, count = 0; + struct ice_pf *pf; + int i; + + pf = hw->back; + for (i = 0; i < numq; i++) { + q_ctx = ice_get_lan_q_ctx(hw, vsi_num, tc, i); + if (!q_ctx) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d NO Q CONTEXT\n", + __func__, i); + continue; + } + if (q_ctx->q_teid == ICE_INVAL_TEID) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL TEID\n", + __func__, i); + continue; + } + if (q_ctx->q_handle == ICE_INVAL_Q_HANDLE) { + dev_dbg(ice_hw_to_dev(hw), "%s queue %d INVAL Q HANDLE\n", + __func__, i); + continue; + } + + qid = pf->vsi[vsi_num]->txq_map[q_ctx->q_handle]; + qbuf->queue_info[count].q_handle = cpu_to_le16(qid); + qbuf->queue_info[count].tc = tc; + qbuf->queue_info[count].q_teid = cpu_to_le32(q_ctx->q_teid); + count++; + } + + return count; +} + +/** + * ice_lag_get_sched_parent - locate or create a sched node parent + * @hw: HW struct for getting parent in + * @tc: traffic class on parent/node + */ +static struct ice_sched_node * +ice_lag_get_sched_parent(struct ice_hw *hw, u8 tc) +{ + struct ice_sched_node *tc_node, *aggnode, *parent = NULL; + u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; + struct ice_port_info *pi = hw->port_info; + struct device *dev; + u8 aggl, vsil; + int n; + + dev = ice_hw_to_dev(hw); + + tc_node = ice_sched_get_tc_node(pi, tc); + if (!tc_node) { + dev_warn(dev, "Failure to find TC node for LAG move\n"); + return parent; + } + + aggnode = ice_sched_get_agg_node(pi, tc_node, ICE_DFLT_AGG_ID); + if (!aggnode) { + dev_warn(dev, "Failure to find aggregate node for LAG move\n"); + return parent; + } + + aggl = ice_sched_get_agg_layer(hw); + vsil = ice_sched_get_vsi_layer(hw); + + for (n = aggl + 1; n < vsil; n++) + num_nodes[n] = 1; + + for (n = 0; n < aggnode->num_children; n++) { + parent = ice_sched_get_free_vsi_parent(hw, aggnode->children[n], + num_nodes); + if (parent) + return parent; + } + + /* if free parent not found - add one */ + parent = aggnode; + for (n = aggl + 1; n < vsil; n++) { + u16 num_nodes_added; + u32 first_teid; + int err; + + err = ice_sched_add_nodes_to_layer(pi, tc_node, parent, n, + num_nodes[n], &first_teid, + &num_nodes_added); + if (err || num_nodes[n] != num_nodes_added) + return NULL; + + if (num_nodes_added) + parent = ice_sched_find_node_by_teid(tc_node, + first_teid); + else + parent = parent->children[0]; + if (!parent) { + dev_warn(dev, "Failure to add new parent for LAG move\n"); + return parent; + } + } + + return parent; +} + +/** + * ice_lag_move_vf_node_tc - move scheduling nodes for one VF on one TC + * @lag: lag info struct + * @oldport: lport of previous nodes location + * @newport: lport of destination nodes location + * @vsi_num: array index of VSI in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num, u8 tc) +{ + u16 numq, valq, buf_size, num_moved, qbuf_size; + struct device *dev = ice_pf_to_dev(lag->pf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_aqc_move_elem *buf; + struct ice_sched_node *n_prt; + struct ice_hw *new_hw = NULL; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + u32 tmp_teid; + + ctx = ice_get_vsi_ctx(&lag->pf->hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG failover\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + /* locate HW struct for destination port */ + new_hw = ice_lag_find_hw_by_lport(lag, newport); + if (!new_hw) { + dev_warn(dev, "Unable to locate HW struct for LAG node destination\n"); + return; + } + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + /* if no teid assigned or numq == 0, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend VSI subtree for Traffic Class "tc" on + * this VF's VSI + */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfigure all VF's queues on this Traffic Class + * to new port + */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_traffic; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(&lag->pf->hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG failover\n"); + goto qbuf_none; + } + + if (ice_aq_cfg_lan_txq(&lag->pf->hw, qbuf, qbuf_size, valq, oldport, + newport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto qbuf_err; + } + +qbuf_none: + kfree(qbuf); + + /* find new parent in destination port's tree for VF VSI node on this + * Traffic Class + */ + n_prt = ice_lag_get_sched_parent(new_hw, tc); + if (!n_prt) + goto resume_traffic; + + /* Move Vf's VSI node for this TC to newport's scheduler tree */ + buf_size = struct_size(buf, teid, 1); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) { + dev_warn(dev, "Failure to alloc memory for VF node failover\n"); + goto resume_traffic; + } + + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved, + NULL)) + dev_warn(dev, "Failure to move VF nodes for failover\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + kfree(buf); + goto resume_traffic; + +qbuf_err: + kfree(qbuf); + +resume_traffic: + /* restart traffic for VSI node */ + if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, false)) + dev_dbg(dev, "Problem restarting traffic for LAG node move\n"); +} + +/** + * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF + * @lag: primary interface LAG struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + * @vsi_num: SW index of VF's VSI + */ +static void +ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport, + u16 vsi_num) +{ + u8 tc; + + ice_for_each_traffic_class(tc) + ice_lag_move_vf_node_tc(lag, oldport, newport, vsi_num, tc); +} + +/** + * ice_lag_move_new_vf_nodes - Move Tx scheduling nodes for a VF if required + * @vf: the VF to move Tx nodes for + * + * Called just after configuring new VF queues. Check whether the VF Tx + * scheduling nodes need to be updated to fail over to the active port. If so, + * move them now. + */ +void ice_lag_move_new_vf_nodes(struct ice_vf *vf) +{ + struct ice_lag_netdev_list ndlist; + struct list_head *tmp, *n; + u8 pri_port, act_port; + struct ice_lag *lag; + struct ice_vsi *vsi; + struct ice_pf *pf; + + vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + if (WARN_ON(vsi->type != ICE_VSI_VF)) + return; + + pf = vf->pf; + lag = pf->lag; + + mutex_lock(&pf->lag_mutex); + if (!lag->bonded) + goto new_vf_unlock; + + pri_port = pf->hw.port_info->lport; + act_port = lag->active_port; + + if (lag->upper_netdev) { + struct ice_lag_netdev_list *nl; + struct net_device *tmp_nd; + + INIT_LIST_HEAD(&ndlist.node); + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + nl = kzalloc(sizeof(*nl), GFP_KERNEL); + if (!nl) + break; + + nl->netdev = tmp_nd; + list_add(&nl->node, &ndlist.node); + } + rcu_read_unlock(); + } + + lag->netdev_head = &ndlist.node; + + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) && + lag->bonded && lag->primary && pri_port != act_port && + !list_empty(lag->netdev_head)) + ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx); + + list_for_each_safe(tmp, n, &ndlist.node) { + struct ice_lag_netdev_list *entry; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + list_del(&entry->node); + kfree(entry); + } + lag->netdev_head = NULL; + +new_vf_unlock: + mutex_unlock(&pf->lag_mutex); +} + +/** + * ice_lag_move_vf_nodes - move Tx scheduling nodes for all VFs to new port + * @lag: lag info struct + * @oldport: lport of previous interface + * @newport: lport of destination interface + */ +static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport) +{ + struct ice_pf *pf; + int i; + + if (!lag->primary) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_lag_move_single_vf_nodes(lag, oldport, newport, i); +} + +#define ICE_LAG_SRIOV_CP_RECIPE 10 +#define ICE_LAG_SRIOV_TRAIN_PKT_LEN 16 + +/** + * ice_lag_cfg_cp_fltr - configure filter for control packets + * @lag: local interface's lag struct + * @add: add or remove rule + */ +static void +ice_lag_cfg_cp_fltr(struct ice_lag *lag, bool add) +{ + struct ice_sw_rule_lkup_rx_tx *s_rule = NULL; + struct ice_vsi *vsi; + u16 buf_len, opc; + + vsi = lag->pf->vsi[0]; + + buf_len = ICE_SW_RULE_RX_TX_HDR_SIZE(s_rule, + ICE_LAG_SRIOV_TRAIN_PKT_LEN); + s_rule = kzalloc(buf_len, GFP_KERNEL); + if (!s_rule) { + netdev_warn(lag->netdev, "-ENOMEM error configuring CP filter\n"); + return; + } + + if (add) { + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->recipe_id = cpu_to_le16(ICE_LAG_SRIOV_CP_RECIPE); + s_rule->src = cpu_to_le16(vsi->port_info->lport); + s_rule->act = cpu_to_le32(ICE_FWD_TO_VSI | + ICE_SINGLE_ACT_LAN_ENABLE | + ICE_SINGLE_ACT_VALID_BIT | + ((vsi->vsi_num << + ICE_SINGLE_ACT_VSI_ID_S) & + ICE_SINGLE_ACT_VSI_ID_M)); + s_rule->hdr_len = cpu_to_le16(ICE_LAG_SRIOV_TRAIN_PKT_LEN); + memcpy(s_rule->hdr_data, lacp_train_pkt, LACP_TRAIN_PKT_LEN); + opc = ice_aqc_opc_add_sw_rules; + } else { + opc = ice_aqc_opc_remove_sw_rules; + s_rule->index = cpu_to_le16(lag->cp_rule_idx); + } + if (ice_aq_sw_rules(&lag->pf->hw, s_rule, buf_len, 1, opc, NULL)) { + netdev_warn(lag->netdev, "Error %s CP rule for fail-over\n", + add ? "ADDING" : "REMOVING"); + goto cp_free; + } + + if (add) + lag->cp_rule_idx = le16_to_cpu(s_rule->index); + else + lag->cp_rule_idx = 0; + +cp_free: + kfree(s_rule); } /** @@ -124,117 +745,430 @@ lag_out: } /** + * ice_lag_reclaim_vf_tc - move scheduling nodes back to primary interface + * @lag: primary interface lag struct + * @src_hw: HW struct current node location + * @vsi_num: VSI index in PF space + * @tc: traffic class to move + */ +static void +ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num, + u8 tc) +{ + u16 numq, valq, buf_size, num_moved, qbuf_size; + struct device *dev = ice_pf_to_dev(lag->pf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_aqc_move_elem *buf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "Unable to locate VSI context for LAG reclaim\n"); + return; + } + + /* check to see if this VF is enabled on this TC */ + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + /* if !teid or !numq, then this TC is not active */ + if (!tmp_teid || !numq) + return; + + /* suspend traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic for LAG node move\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); + goto resume_reclaim; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_dbg(dev, "No valid queues found for LAG reclaim\n"); + goto reclaim_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, + src_hw->port_info->lport, hw->port_info->lport, + NULL)) { + dev_warn(dev, "Failure to configure queues for LAG failover\n"); + goto reclaim_qerr; + } + +reclaim_none: + kfree(qbuf); + + /* find parent in primary tree */ + n_prt = ice_lag_get_sched_parent(hw, tc); + if (!n_prt) + goto resume_reclaim; + + /* Move node to new parent */ + buf_size = struct_size(buf, teid, 1); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) { + dev_warn(dev, "Failure to alloc memory for VF node failover\n"); + goto resume_reclaim; + } + + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved, + NULL)) + dev_warn(dev, "Failure to move VF nodes for LAG reclaim\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + kfree(buf); + goto resume_reclaim; + +reclaim_qerr: + kfree(qbuf); + +resume_reclaim: + /* restart traffic */ + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reclaim\n"); +} + +/** + * ice_lag_reclaim_vf_nodes - When interface leaving bond primary reclaims nodes + * @lag: primary interface lag struct + * @src_hw: HW struct for current node location + */ +static void +ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !src_hw) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_for_each_traffic_class(tc) + ice_lag_reclaim_vf_tc(lag, src_hw, i, tc); +} + +/** * ice_lag_link - handle LAG link event * @lag: LAG info struct - * @info: info from the netdev notifier */ -static void -ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) +static void ice_lag_link(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; struct ice_pf *pf = lag->pf; - int peers = 0; if (lag->bonded) dev_warn(ice_pf_to_dev(pf), "%s Already part of a bond\n", netdev_name(lag->netdev)); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) - peers++; - rcu_read_unlock(); - - if (lag->upper_netdev != upper) { - dev_hold(upper); - lag->upper_netdev = upper; - } - - ice_clear_rdma_cap(pf); - lag->bonded = true; lag->role = ICE_LAG_UNSET; - - /* if this is the first element in an LAG mark as primary */ - lag->primary = !!(peers == 1); + netdev_info(lag->netdev, "Shared SR-IOV resources in bond are active\n"); } /** * ice_lag_unlink - handle unlink event * @lag: LAG info struct - * @info: info from netdev notification */ -static void -ice_lag_unlink(struct ice_lag *lag, - struct netdev_notifier_changeupper_info *info) +static void ice_lag_unlink(struct ice_lag *lag) { - struct net_device *netdev_tmp, *upper = info->upper_dev; + u8 pri_port, act_port, loc_port; struct ice_pf *pf = lag->pf; - bool found = false; if (!lag->bonded) { netdev_dbg(lag->netdev, "bonding unlink event on non-LAG netdev\n"); return; } - /* determine if we are in the new LAG config or not */ - rcu_read_lock(); - for_each_netdev_in_bond_rcu(upper, netdev_tmp) { - if (netdev_tmp == lag->netdev) { - found = true; - break; + if (lag->primary) { + act_port = lag->active_port; + pri_port = lag->pf->hw.port_info->lport; + if (act_port != pri_port && act_port != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes(lag, act_port, pri_port); + lag->primary = false; + lag->active_port = ICE_LAG_INVALID_PORT; + } else { + struct ice_lag *primary_lag; + + primary_lag = ice_lag_find_primary(lag); + if (primary_lag) { + act_port = primary_lag->active_port; + pri_port = primary_lag->pf->hw.port_info->lport; + loc_port = pf->hw.port_info->lport; + if (act_port == loc_port && + act_port != ICE_LAG_INVALID_PORT) { + ice_lag_reclaim_vf_nodes(primary_lag, + &lag->pf->hw); + primary_lag->active_port = ICE_LAG_INVALID_PORT; + } } } - rcu_read_unlock(); - if (found) + lag->bonded = false; + lag->role = ICE_LAG_NONE; + lag->upper_netdev = NULL; +} + +/** + * ice_lag_link_unlink - helper function to call lag_link/unlink + * @lag: lag info struct + * @ptr: opaque pointer data + */ +static void ice_lag_link_unlink(struct ice_lag *lag, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + + if (netdev != lag->netdev) return; - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; + if (info->linking) + ice_lag_link(lag); + else + ice_lag_unlink(lag); +} + +/** + * ice_lag_set_swid - set the SWID on secondary interface + * @primary_swid: primary interface's SWID + * @local_lag: local interfaces LAG struct + * @link: Is this a linking activity + * + * If link is false, then primary_swid should be expected to not be valid + * This function should never be called in interrupt context. + */ +static void +ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag, + bool link) +{ + struct ice_aqc_alloc_free_res_elem *buf; + struct ice_aqc_set_port_params *cmd; + struct ice_aq_desc desc; + u16 buf_len, swid; + int status, i; + + buf_len = struct_size(buf, elem, 1); + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) { + dev_err(ice_pf_to_dev(local_lag->pf), "-ENOMEM error setting SWID\n"); + return; } - lag->peer_netdev = NULL; - ice_set_rdma_cap(pf); - lag->bonded = false; - lag->role = ICE_LAG_NONE; + buf->num_elems = cpu_to_le16(1); + buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_SWID); + /* if unlinnking need to free the shared resource */ + if (!link && local_lag->bond_swid) { + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, + buf_len, ice_aqc_opc_free_res); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error freeing SWID during LAG unlink\n"); + local_lag->bond_swid = 0; + } + + if (link) { + buf->res_type |= cpu_to_le16(ICE_LAG_RES_SHARED | + ICE_LAG_RES_VALID); + /* store the primary's SWID in case it leaves bond first */ + local_lag->bond_swid = primary_swid; + buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid); + } else { + buf->elem[0].e.sw_resp = + cpu_to_le16(local_lag->pf->hw.port_info->sw_id); + } + + status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, buf_len, + ice_aqc_opc_alloc_res); + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error subscribing to SWID 0x%04X\n", + local_lag->bond_swid); + + kfree(buf); + + /* Configure port param SWID to correct value */ + if (link) + swid = primary_swid; + else + swid = local_lag->pf->hw.port_info->sw_id; + + cmd = &desc.params.set_port_params; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params); + + cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid); + /* If this is happening in reset context, it is possible that the + * primary interface has not finished setting its SWID to SHARED + * yet. Allow retries to account for this timing issue between + * interfaces. + */ + for (i = 0; i < ICE_LAG_RESET_RETRIES; i++) { + status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0, + NULL); + if (!status) + break; + + usleep_range(1000, 2000); + } + + if (status) + dev_err(ice_pf_to_dev(local_lag->pf), "Error setting SWID in port params %d\n", + status); } /** - * ice_lag_unregister - handle netdev unregister events - * @lag: LAG info struct - * @netdev: netdev reporting the event + * ice_lag_primary_swid - set/clear the SHARED attrib of primary's SWID + * @lag: primary interface's lag struct + * @link: is this a linking activity + * + * Implement setting primary SWID as shared using 0x020B */ -static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev) +static void ice_lag_primary_swid(struct ice_lag *lag, bool link) { - struct ice_pf *pf = lag->pf; + struct ice_hw *hw; + u16 swid; - /* check to see if this event is for this netdev - * check that we are in an aggregate - */ - if (netdev != lag->netdev || !lag->bonded) + hw = &lag->pf->hw; + swid = hw->port_info->sw_id; + + if (ice_share_res(hw, ICE_AQC_RES_TYPE_SWID, link, swid)) + dev_warn(ice_pf_to_dev(lag->pf), "Failure to set primary interface shared status\n"); +} + +/** + * ice_lag_add_prune_list - Adds event_pf's VSI to primary's prune list + * @lag: lag info struct + * @event_pf: PF struct for VSI we are adding to primary's prune list + */ +static void ice_lag_add_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, rule_buf_sz, vsi_list_id, event_vsi_num, prim_vsi_idx; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + event_vsi_num = event_pf->vsi[0]->vsi_num; + prim_vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + prim_vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when setting up SRIOV LAG\n"); return; + } - if (lag->upper_netdev) { - dev_put(lag->upper_netdev); - lag->upper_netdev = NULL; - ice_set_rdma_cap(pf); + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating space for prune list when configuring SRIOV LAG\n"); + return; } - /* perform some cleanup in case we come back */ - lag->bonded = false; - lag->role = ICE_LAG_NONE; + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_SET); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(event_vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, s_rule, rule_buf_sz, 1, + ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error adding VSI prune list\n"); + kfree(s_rule); +} + +/** + * ice_lag_del_prune_list - Remove secondary's vsi from primary's prune list + * @lag: primary interface's ice_lag struct + * @event_pf: PF struct for unlinking interface + */ +static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf) +{ + u16 num_vsi, vsi_num, vsi_idx, rule_buf_sz, vsi_list_id; + struct ice_sw_rule_vsi_list *s_rule = NULL; + struct device *dev; + + num_vsi = 1; + + dev = ice_pf_to_dev(lag->pf); + vsi_num = event_pf->vsi[0]->vsi_num; + vsi_idx = lag->pf->vsi[0]->idx; + + if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN, + vsi_idx, &vsi_list_id)) { + dev_warn(dev, "Could not locate prune list when unwinding SRIOV LAG\n"); + return; + } + + rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi); + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) { + dev_warn(dev, "Error allocating prune list when unwinding SRIOV LAG\n"); + return; + } + + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR); + s_rule->index = cpu_to_le16(vsi_list_id); + s_rule->number_vsi = cpu_to_le16(num_vsi); + s_rule->vsi[0] = cpu_to_le16(vsi_num); + + if (ice_aq_sw_rules(&event_pf->hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, ice_aqc_opc_update_sw_rules, NULL)) + dev_warn(dev, "Error clearing VSI prune list\n"); + + kfree(s_rule); +} + +/** + * ice_lag_init_feature_support_flag - Check for NVM support for LAG + * @pf: PF struct + */ +static void ice_lag_init_feature_support_flag(struct ice_pf *pf) +{ + struct ice_hw_common_caps *caps; + + caps = &pf->hw.dev_caps.common_cap; + if (caps->roce_lag) + ice_set_feature_support(pf, ICE_F_ROCE_LAG); + else + ice_clear_feature_support(pf, ICE_F_ROCE_LAG); + + if (caps->sriov_lag) + ice_set_feature_support(pf, ICE_F_SRIOV_LAG); + else + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); } /** * ice_lag_changeupper_event - handle LAG changeupper event * @lag: LAG info struct * @ptr: opaque pointer data - * - * ptr is to be cast into netdev_notifier_changeupper_info */ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) { struct netdev_notifier_changeupper_info *info; + struct ice_lag *primary_lag; struct net_device *netdev; info = ptr; @@ -244,44 +1178,442 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) if (netdev != lag->netdev) return; - if (!info->upper_dev) { - netdev_dbg(netdev, "changeupper rcvd, but no upper defined\n"); + primary_lag = ice_lag_find_primary(lag); + if (info->linking) { + lag->upper_netdev = info->upper_dev; + /* If there is not already a primary interface in the LAG, + * then mark this one as primary. + */ + if (!primary_lag) { + lag->primary = true; + /* Configure primary's SWID to be shared */ + ice_lag_primary_swid(lag, true); + primary_lag = lag; + } else { + u16 swid; + + swid = primary_lag->pf->hw.port_info->sw_id; + ice_lag_set_swid(swid, lag, true); + ice_lag_add_prune_list(primary_lag, lag->pf); + } + /* add filter for primary control packets */ + ice_lag_cfg_cp_fltr(lag, true); + } else { + if (!primary_lag && lag->primary) + primary_lag = lag; + + if (!lag->primary) { + ice_lag_set_swid(0, lag, false); + } else { + if (primary_lag && lag->primary) { + ice_lag_primary_swid(lag, false); + ice_lag_del_prune_list(primary_lag, lag->pf); + } + } + /* remove filter for control packets */ + ice_lag_cfg_cp_fltr(lag, false); + } +} + +/** + * ice_lag_monitor_link - monitor interfaces entering/leaving the aggregate + * @lag: lag info struct + * @ptr: opaque data containing notifier event + * + * This function only operates after a primary has been set. + */ +static void ice_lag_monitor_link(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct ice_hw *prim_hw, *active_hw; + struct net_device *event_netdev; + struct ice_pf *pf; + u8 prim_port; + + if (!lag->primary) + return; + + event_netdev = netdev_notifier_info_to_dev(ptr); + if (!netif_is_same_ice(lag->pf, event_netdev)) + return; + + pf = lag->pf; + prim_hw = &pf->hw; + prim_port = prim_hw->port_info->lport; + + info = (struct netdev_notifier_changeupper_info *)ptr; + if (info->upper_dev != lag->upper_netdev) return; + + if (!info->linking) { + /* Since there are only two interfaces allowed in SRIOV+LAG, if + * one port is leaving, then nodes need to be on primary + * interface. + */ + if (prim_port != lag->active_port && + lag->active_port != ICE_LAG_INVALID_PORT) { + active_hw = ice_lag_find_hw_by_lport(lag, + lag->active_port); + ice_lag_reclaim_vf_nodes(lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } } +} + +/** + * ice_lag_monitor_active - main PF keep track of which port is active + * @lag: lag info struct + * @ptr: opaque data containing notifier event + * + * This function is for the primary PF to monitor changes in which port is + * active and handle changes for SRIOV VF functionality + */ +static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct ice_netdev_priv *event_np; + struct ice_pf *pf, *event_pf; + u8 prim_port, event_port; + + if (!lag->primary) + return; - netdev_dbg(netdev, "bonding %s\n", info->linking ? "LINK" : "UNLINK"); + pf = lag->pf; + if (!pf) + return; - if (!netif_is_lag_master(info->upper_dev)) { - netdev_dbg(netdev, "changeupper rcvd, but not primary. bail\n"); + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (!netif_is_ice(event_netdev) || event_upper != lag->upper_netdev) return; + + event_np = netdev_priv(event_netdev); + event_pf = event_np->vsi->back; + event_port = event_pf->hw.port_info->lport; + prim_port = pf->hw.port_info->lport; + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + + if (!bonding_info->slave.state) { + /* if no port is currently active, then nodes and filters exist + * on primary port, check if we need to move them + */ + if (lag->active_port == ICE_LAG_INVALID_PORT) { + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, prim_port, + event_port); + lag->active_port = event_port; + return; + } + + /* active port is already set and is current event port */ + if (lag->active_port == event_port) + return; + /* new active port */ + ice_lag_move_vf_nodes(lag, lag->active_port, event_port); + lag->active_port = event_port; + } else { + /* port not set as currently active (e.g. new active port + * has already claimed the nodes and filters + */ + if (lag->active_port != event_port) + return; + /* This is the case when neither port is active (both link down) + * Link down on the bond - set active port to invalid and move + * nodes and filters back to primary if not already there + */ + if (event_port != prim_port) + ice_lag_move_vf_nodes(lag, event_port, prim_port); + lag->active_port = ICE_LAG_INVALID_PORT; } +} - if (info->linking) - ice_lag_link(lag, info); - else - ice_lag_unlink(lag, info); +/** + * ice_lag_chk_comp - evaluate bonded interface for feature support + * @lag: lag info struct + * @ptr: opaque data for netdev event info + */ +static bool +ice_lag_chk_comp(struct ice_lag *lag, void *ptr) +{ + struct net_device *event_netdev, *event_upper; + struct netdev_notifier_bonding_info *info; + struct netdev_bonding_info *bonding_info; + struct list_head *tmp; + struct device *dev; + int count = 0; - ice_display_lag_info(lag); + if (!lag->primary) + return true; + + event_netdev = netdev_notifier_info_to_dev(ptr); + rcu_read_lock(); + event_upper = netdev_master_upper_dev_get_rcu(event_netdev); + rcu_read_unlock(); + if (event_upper != lag->upper_netdev) + return true; + + dev = ice_pf_to_dev(lag->pf); + + /* only supporting switchdev mode for SRIOV VF LAG. + * primary interface has to be in switchdev mode + */ + if (!ice_is_switchdev_running(lag->pf)) { + dev_info(dev, "Primary interface not in switchdev mode - VF LAG disabled\n"); + return false; + } + + info = (struct netdev_notifier_bonding_info *)ptr; + bonding_info = &info->bonding_info; + lag->bond_mode = bonding_info->master.bond_mode; + if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) { + dev_info(dev, "Bond Mode not ACTIVE-BACKUP - VF LAG disabled\n"); + return false; + } + + list_for_each(tmp, lag->netdev_head) { + struct ice_dcbx_cfg *dcb_cfg, *peer_dcb_cfg; + struct ice_lag_netdev_list *entry; + struct ice_netdev_priv *peer_np; + struct net_device *peer_netdev; + struct ice_vsi *vsi, *peer_vsi; + struct ice_pf *peer_pf; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + peer_netdev = entry->netdev; + if (!netif_is_ice(peer_netdev)) { + dev_info(dev, "Found %s non-ice netdev in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + count++; + if (count > 2) { + dev_info(dev, "Found more than two netdevs in LAG - VF LAG disabled\n"); + return false; + } + + peer_np = netdev_priv(peer_netdev); + vsi = ice_get_main_vsi(lag->pf); + peer_vsi = peer_np->vsi; + if (lag->pf->pdev->bus != peer_vsi->back->pdev->bus || + lag->pf->pdev->slot != peer_vsi->back->pdev->slot) { + dev_info(dev, "Found %s on different device in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + dcb_cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg; + peer_dcb_cfg = &peer_vsi->port_info->qos_cfg.local_dcbx_cfg; + if (memcmp(dcb_cfg, peer_dcb_cfg, + sizeof(struct ice_dcbx_cfg))) { + dev_info(dev, "Found %s with different DCB in LAG - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + + peer_pf = peer_vsi->back; + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, peer_pf->flags)) { + dev_warn(dev, "Found %s with FW LLDP agent active - VF LAG disabled\n", + netdev_name(peer_netdev)); + return false; + } + } + + return true; } /** - * ice_lag_changelower_event - handle LAG changelower event + * ice_lag_unregister - handle netdev unregister events * @lag: LAG info struct - * @ptr: opaque data pointer + * @event_netdev: netdev struct for target of notifier event + */ +static void +ice_lag_unregister(struct ice_lag *lag, struct net_device *event_netdev) +{ + struct ice_netdev_priv *np; + struct ice_pf *event_pf; + struct ice_lag *p_lag; + + p_lag = ice_lag_find_primary(lag); + np = netdev_priv(event_netdev); + event_pf = np->vsi->back; + + if (p_lag) { + if (p_lag->active_port != p_lag->pf->hw.port_info->lport && + p_lag->active_port != ICE_LAG_INVALID_PORT) { + struct ice_hw *active_hw; + + active_hw = ice_lag_find_hw_by_lport(lag, + p_lag->active_port); + if (active_hw) + ice_lag_reclaim_vf_nodes(p_lag, active_hw); + lag->active_port = ICE_LAG_INVALID_PORT; + } + } + + /* primary processing for primary */ + if (lag->primary && lag->netdev == event_netdev) + ice_lag_primary_swid(lag, false); + + /* primary processing for secondary */ + if (lag->primary && lag->netdev != event_netdev) + ice_lag_del_prune_list(lag, event_pf); + + /* secondary processing for secondary */ + if (!lag->primary && lag->netdev == event_netdev) + ice_lag_set_swid(0, lag, false); +} + +/** + * ice_lag_monitor_rdma - set and clear rdma functionality + * @lag: pointer to lag struct + * @ptr: opaque data for netdev event info + */ +static void +ice_lag_monitor_rdma(struct ice_lag *lag, void *ptr) +{ + struct netdev_notifier_changeupper_info *info; + struct net_device *netdev; + + info = ptr; + netdev = netdev_notifier_info_to_dev(ptr); + + if (netdev != lag->netdev) + return; + + if (info->linking) + ice_clear_rdma_cap(lag->pf); + else + ice_set_rdma_cap(lag->pf); +} + +/** + * ice_lag_chk_disabled_bond - monitor interfaces entering/leaving disabled bond + * @lag: lag info struct + * @ptr: opaque data containing event * - * ptr to be cast to netdev_notifier_changelowerstate_info + * as interfaces enter a bond - determine if the bond is currently + * SRIOV LAG compliant and flag if not. As interfaces leave the + * bond, reset their compliant status. */ -static void ice_lag_changelower_event(struct ice_lag *lag, void *ptr) +static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct ice_lag *prim_lag; if (netdev != lag->netdev) return; - netdev_dbg(netdev, "bonding info\n"); + if (info->linking) { + prim_lag = ice_lag_find_primary(lag); + if (prim_lag && + !ice_is_feature_supported(prim_lag->pf, ICE_F_SRIOV_LAG)) { + ice_clear_feature_support(lag->pf, ICE_F_SRIOV_LAG); + netdev_info(netdev, "Interface added to non-compliant SRIOV LAG aggregate\n"); + } + } else { + ice_lag_init_feature_support_flag(lag->pf); + } +} + +/** + * ice_lag_disable_sriov_bond - set members of bond as not supporting SRIOV LAG + * @lag: primary interfaces lag struct + */ +static void ice_lag_disable_sriov_bond(struct ice_lag *lag) +{ + struct ice_lag_netdev_list *entry; + struct ice_netdev_priv *np; + struct net_device *netdev; + struct ice_pf *pf; + + list_for_each_entry(entry, lag->netdev_head, node) { + netdev = entry->netdev; + np = netdev_priv(netdev); + pf = np->vsi->back; + + ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); + } +} + +/** + * ice_lag_process_event - process a task assigned to the lag_wq + * @work: pointer to work_struct + */ +static void ice_lag_process_event(struct work_struct *work) +{ + struct netdev_notifier_changeupper_info *info; + struct ice_lag_work *lag_work; + struct net_device *netdev; + struct list_head *tmp, *n; + struct ice_pf *pf; + + lag_work = container_of(work, struct ice_lag_work, lag_task); + pf = lag_work->lag->pf; + + mutex_lock(&pf->lag_mutex); + lag_work->lag->netdev_head = &lag_work->netdev_list.node; + + switch (lag_work->event) { + case NETDEV_CHANGEUPPER: + info = &lag_work->info.changeupper_info; + ice_lag_chk_disabled_bond(lag_work->lag, info); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + ice_lag_monitor_link(lag_work->lag, info); + ice_lag_changeupper_event(lag_work->lag, info); + ice_lag_link_unlink(lag_work->lag, info); + } + ice_lag_monitor_rdma(lag_work->lag, info); + break; + case NETDEV_BONDING_INFO: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + if (!ice_lag_chk_comp(lag_work->lag, + &lag_work->info.bonding_info)) { + netdev = lag_work->info.bonding_info.info.dev; + ice_lag_disable_sriov_bond(lag_work->lag); + ice_lag_unregister(lag_work->lag, netdev); + goto lag_cleanup; + } + ice_lag_monitor_active(lag_work->lag, + &lag_work->info.bonding_info); + ice_lag_cfg_pf_fltrs(lag_work->lag, + &lag_work->info.bonding_info); + } + ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info); + break; + case NETDEV_UNREGISTER: + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { + netdev = lag_work->info.bonding_info.info.dev; + if ((netdev == lag_work->lag->netdev || + lag_work->lag->primary) && lag_work->lag->bonded) + ice_lag_unregister(lag_work->lag, netdev); + } + break; + default: + break; + } + +lag_cleanup: + /* cleanup resources allocated for this work item */ + list_for_each_safe(tmp, n, &lag_work->netdev_list.node) { + struct ice_lag_netdev_list *entry; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + list_del(&entry->node); + kfree(entry); + } + lag_work->lag->netdev_head = NULL; - if (!netif_is_lag_port(netdev)) - netdev_dbg(netdev, "CHANGELOWER rcvd, but netdev not in LAG. Bail\n"); + mutex_unlock(&pf->lag_mutex); + + kfree(lag_work); } /** @@ -295,34 +1627,79 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct net_device *upper_netdev; + struct ice_lag_work *lag_work; struct ice_lag *lag; - lag = container_of(notif_blk, struct ice_lag, notif_block); + if (!netif_is_ice(netdev)) + return NOTIFY_DONE; + + if (event != NETDEV_CHANGEUPPER && event != NETDEV_BONDING_INFO && + event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + if (!(netdev->priv_flags & IFF_BONDING)) + return NOTIFY_DONE; + lag = container_of(notif_blk, struct ice_lag, notif_block); if (!lag->netdev) return NOTIFY_DONE; - /* Check that the netdev is in the working namespace */ if (!net_eq(dev_net(netdev), &init_net)) return NOTIFY_DONE; + /* This memory will be freed at the end of ice_lag_process_event */ + lag_work = kzalloc(sizeof(*lag_work), GFP_KERNEL); + if (!lag_work) + return -ENOMEM; + + lag_work->event_netdev = netdev; + lag_work->lag = lag; + lag_work->event = event; + if (event == NETDEV_CHANGEUPPER) { + struct netdev_notifier_changeupper_info *info; + + info = ptr; + upper_netdev = info->upper_dev; + } else { + upper_netdev = netdev_master_upper_dev_get(netdev); + } + + INIT_LIST_HEAD(&lag_work->netdev_list.node); + if (upper_netdev) { + struct ice_lag_netdev_list *nd_list; + struct net_device *tmp_nd; + + rcu_read_lock(); + for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) { + nd_list = kzalloc(sizeof(*nd_list), GFP_KERNEL); + if (!nd_list) + break; + + nd_list->netdev = tmp_nd; + list_add(&nd_list->node, &lag_work->netdev_list.node); + } + rcu_read_unlock(); + } + switch (event) { case NETDEV_CHANGEUPPER: - ice_lag_changeupper_event(lag, ptr); - break; - case NETDEV_CHANGELOWERSTATE: - ice_lag_changelower_event(lag, ptr); + lag_work->info.changeupper_info = + *((struct netdev_notifier_changeupper_info *)ptr); break; case NETDEV_BONDING_INFO: - ice_lag_info_event(lag, ptr); - break; - case NETDEV_UNREGISTER: - ice_lag_unregister(lag, netdev); + lag_work->info.bonding_info = + *((struct netdev_notifier_bonding_info *)ptr); break; default: + lag_work->info.notifier_info = + *((struct netdev_notifier_info *)ptr); break; } + INIT_WORK(&lag_work->lag_task, ice_lag_process_event); + queue_work(ice_lag_wq, &lag_work->lag_task); + return NOTIFY_DONE; } @@ -366,6 +1743,174 @@ static void ice_unregister_lag_handler(struct ice_lag *lag) } /** + * ice_create_lag_recipe + * @hw: pointer to HW struct + * @rid: pointer to u16 to pass back recipe index + * @base_recipe: recipe to base the new recipe on + * @prio: priority for new recipe + * + * function returns 0 on error + */ +static int ice_create_lag_recipe(struct ice_hw *hw, u16 *rid, + const u8 *base_recipe, u8 prio) +{ + struct ice_aqc_recipe_data_elem *new_rcp; + int err; + + err = ice_alloc_recipe(hw, rid); + if (err) + return err; + + new_rcp = kzalloc(ICE_RECIPE_LEN * ICE_MAX_NUM_RECIPES, GFP_KERNEL); + if (!new_rcp) + return -ENOMEM; + + memcpy(new_rcp, base_recipe, ICE_RECIPE_LEN); + new_rcp->content.act_ctrl_fwd_priority = prio; + new_rcp->content.rid = *rid | ICE_AQ_RECIPE_ID_IS_ROOT; + new_rcp->recipe_indx = *rid; + bitmap_zero((unsigned long *)new_rcp->recipe_bitmap, + ICE_MAX_NUM_RECIPES); + set_bit(*rid, (unsigned long *)new_rcp->recipe_bitmap); + + err = ice_aq_add_recipe(hw, new_rcp, 1, NULL); + if (err) + *rid = 0; + + kfree(new_rcp); + return err; +} + +/** + * ice_lag_move_vf_nodes_tc_sync - move a VF's nodes for a tc during reset + * @lag: primary interfaces lag struct + * @dest_hw: HW struct for destination's interface + * @vsi_num: VSI index in PF space + * @tc: traffic class to move + */ +static void +ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw, + u16 vsi_num, u8 tc) +{ + u16 numq, valq, buf_size, num_moved, qbuf_size; + struct device *dev = ice_pf_to_dev(lag->pf); + struct ice_aqc_cfg_txqs_buf *qbuf; + struct ice_aqc_move_elem *buf; + struct ice_sched_node *n_prt; + __le32 teid, parent_teid; + struct ice_vsi_ctx *ctx; + struct ice_hw *hw; + u32 tmp_teid; + + hw = &lag->pf->hw; + ctx = ice_get_vsi_ctx(hw, vsi_num); + if (!ctx) { + dev_warn(dev, "LAG rebuild failed after reset due to VSI Context failure\n"); + return; + } + + if (!ctx->sched.vsi_node[tc]) + return; + + numq = ctx->num_lan_q_entries[tc]; + teid = ctx->sched.vsi_node[tc]->info.node_teid; + tmp_teid = le32_to_cpu(teid); + parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; + + if (!tmp_teid || !numq) + return; + + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true)) + dev_dbg(dev, "Problem suspending traffic during reset rebuild\n"); + + /* reconfig queues for new port */ + qbuf_size = struct_size(qbuf, queue_info, numq); + qbuf = kzalloc(qbuf_size, GFP_KERNEL); + if (!qbuf) { + dev_warn(dev, "Failure allocating VF queue recfg buffer for reset rebuild\n"); + goto resume_sync; + } + + /* add the per queue info for the reconfigure command buffer */ + valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); + if (!valq) { + dev_warn(dev, "Failure to reconfig queues for LAG reset rebuild\n"); + goto sync_none; + } + + if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, hw->port_info->lport, + dest_hw->port_info->lport, NULL)) { + dev_warn(dev, "Failure to configure queues for LAG reset rebuild\n"); + goto sync_qerr; + } + +sync_none: + kfree(qbuf); + + /* find parent in destination tree */ + n_prt = ice_lag_get_sched_parent(dest_hw, tc); + if (!n_prt) + goto resume_sync; + + /* Move node to new parent */ + buf_size = struct_size(buf, teid, 1); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) { + dev_warn(dev, "Failure to alloc for VF node move in reset rebuild\n"); + goto resume_sync; + } + + buf->hdr.src_parent_teid = parent_teid; + buf->hdr.dest_parent_teid = n_prt->info.node_teid; + buf->hdr.num_elems = cpu_to_le16(1); + buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN; + buf->teid[0] = teid; + + if (ice_aq_move_sched_elems(&lag->pf->hw, 1, buf, buf_size, &num_moved, + NULL)) + dev_warn(dev, "Failure to move VF nodes for LAG reset rebuild\n"); + else + ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]); + + kfree(buf); + goto resume_sync; + +sync_qerr: + kfree(qbuf); + +resume_sync: + if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false)) + dev_warn(dev, "Problem restarting traffic for LAG node reset rebuild\n"); +} + +/** + * ice_lag_move_vf_nodes_sync - move vf nodes to active interface + * @lag: primary interfaces lag struct + * @dest_hw: lport value for currently active port + * + * This function is used in a reset context, outside of event handling, + * to move the VF nodes to the secondary interface when that interface + * is the active interface during a reset rebuild + */ +static void +ice_lag_move_vf_nodes_sync(struct ice_lag *lag, struct ice_hw *dest_hw) +{ + struct ice_pf *pf; + int i, tc; + + if (!lag->primary || !dest_hw) + return; + + pf = lag->pf; + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && (pf->vsi[i]->type == ICE_VSI_VF || + pf->vsi[i]->type == ICE_VSI_SWITCHDEV_CTRL)) + ice_for_each_traffic_class(tc) + ice_lag_move_vf_nodes_tc_sync(lag, dest_hw, i, + tc); +} + +/** * ice_init_lag - initialize support for LAG * @pf: PF struct * @@ -377,7 +1922,10 @@ int ice_init_lag(struct ice_pf *pf) struct device *dev = ice_pf_to_dev(pf); struct ice_lag *lag; struct ice_vsi *vsi; - int err; + u64 recipe_bits = 0; + int n, err; + + ice_lag_init_feature_support_flag(pf); pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL); if (!pf->lag) @@ -394,8 +1942,8 @@ int ice_init_lag(struct ice_pf *pf) lag->pf = pf; lag->netdev = vsi->netdev; lag->role = ICE_LAG_NONE; + lag->active_port = ICE_LAG_INVALID_PORT; lag->bonded = false; - lag->peer_netdev = NULL; lag->upper_netdev = NULL; lag->notif_block.notifier_call = NULL; @@ -405,6 +1953,25 @@ int ice_init_lag(struct ice_pf *pf) goto lag_error; } + err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, ice_dflt_vsi_rcp, + 1); + if (err) + goto lag_error; + + /* associate recipes to profiles */ + for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) { + err = ice_aq_get_recipe_to_profile(&pf->hw, n, + (u8 *)&recipe_bits, NULL); + if (err) + continue; + + if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) { + recipe_bits |= BIT(lag->pf_recipe); + ice_aq_map_recipe_to_profile(&pf->hw, n, + (u8 *)&recipe_bits, NULL); + } + } + ice_display_lag_info(lag); dev_dbg(dev, "INIT LAG complete\n"); @@ -435,11 +2002,94 @@ void ice_deinit_lag(struct ice_pf *pf) if (lag->pf) ice_unregister_lag_handler(lag); - dev_put(lag->upper_netdev); + flush_workqueue(ice_lag_wq); - dev_put(lag->peer_netdev); + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->pf_recipe); kfree(lag); pf->lag = NULL; } + +/** + * ice_lag_rebuild - rebuild lag resources after reset + * @pf: pointer to local pf struct + * + * PF resets are promoted to CORER resets when interface in an aggregate. This + * means that we need to rebuild the PF resources for the interface. Since + * this will happen outside the normal event processing, need to acquire the lag + * lock. + * + * This function will also evaluate the VF resources if this is the primary + * interface. + */ +void ice_lag_rebuild(struct ice_pf *pf) +{ + struct ice_lag_netdev_list ndlist; + struct ice_lag *lag, *prim_lag; + struct list_head *tmp, *n; + u8 act_port, loc_port; + + if (!pf->lag || !pf->lag->bonded) + return; + + mutex_lock(&pf->lag_mutex); + + lag = pf->lag; + if (lag->primary) { + prim_lag = lag; + } else { + struct ice_lag_netdev_list *nl; + struct net_device *tmp_nd; + + INIT_LIST_HEAD(&ndlist.node); + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + nl = kzalloc(sizeof(*nl), GFP_KERNEL); + if (!nl) + break; + + nl->netdev = tmp_nd; + list_add(&nl->node, &ndlist.node); + } + rcu_read_unlock(); + lag->netdev_head = &ndlist.node; + prim_lag = ice_lag_find_primary(lag); + } + + if (!prim_lag) { + dev_dbg(ice_pf_to_dev(pf), "No primary interface in aggregate, can't rebuild\n"); + goto lag_rebuild_out; + } + + act_port = prim_lag->active_port; + loc_port = lag->pf->hw.port_info->lport; + + /* configure SWID for this port */ + if (lag->primary) { + ice_lag_primary_swid(lag, true); + } else { + ice_lag_set_swid(prim_lag->pf->hw.port_info->sw_id, lag, true); + ice_lag_add_prune_list(prim_lag, pf); + if (act_port == loc_port) + ice_lag_move_vf_nodes_sync(prim_lag, &pf->hw); + } + + ice_lag_cfg_cp_fltr(lag, true); + + if (lag->pf_rule_id) + if (ice_lag_cfg_dflt_fltr(lag, true)) + dev_err(ice_pf_to_dev(pf), "Error adding default VSI rule in rebuild\n"); + + ice_clear_rdma_cap(pf); +lag_rebuild_out: + list_for_each_safe(tmp, n, &ndlist.node) { + struct ice_lag_netdev_list *entry; + + entry = list_entry(tmp, struct ice_lag_netdev_list, node); + list_del(&entry->node); + kfree(entry); + } + mutex_unlock(&pf->lag_mutex); +} diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index 2c373676c42f..18075b82485a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -14,20 +14,52 @@ enum ice_lag_role { ICE_LAG_UNSET }; +#define ICE_LAG_INVALID_PORT 0xFF + +#define ICE_LAG_RESET_RETRIES 5 + struct ice_pf; +struct ice_vf; + +struct ice_lag_netdev_list { + struct list_head node; + struct net_device *netdev; +}; /* LAG info struct */ struct ice_lag { struct ice_pf *pf; /* backlink to PF struct */ struct net_device *netdev; /* this PF's netdev */ - struct net_device *peer_netdev; struct net_device *upper_netdev; /* upper bonding netdev */ + struct list_head *netdev_head; struct notifier_block notif_block; + s32 bond_mode; + u16 bond_swid; /* swid for primary interface */ + u8 active_port; /* lport value for the current active port */ u8 bonded:1; /* currently bonded */ u8 primary:1; /* this is primary */ + u16 pf_recipe; + u16 pf_rule_id; + u16 cp_rule_idx; u8 role; }; +/* LAG workqueue struct */ +struct ice_lag_work { + struct work_struct lag_task; + struct ice_lag_netdev_list netdev_list; + struct ice_lag *lag; + unsigned long event; + struct net_device *event_netdev; + union { + struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_bonding_info bonding_info; + struct netdev_notifier_info notifier_info; + } info; +}; + +void ice_lag_move_new_vf_nodes(struct ice_vf *vf); int ice_init_lag(struct ice_pf *pf); void ice_deinit_lag(struct ice_pf *pf); +void ice_lag_rebuild(struct ice_pf *pf); #endif /* _ICE_LAG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 00e3afd507a4..201570cd2e0b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -907,6 +907,7 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) { struct ice_hw_common_caps *cap; struct ice_pf *pf = vsi->back; + u16 max_rss_size; if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { vsi->rss_size = 1; @@ -914,32 +915,31 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) } cap = &pf->hw.func_caps.common_cap; + max_rss_size = BIT(cap->rss_table_entry_width); switch (vsi->type) { case ICE_VSI_CHNL: case ICE_VSI_PF: /* PF VSI will inherit RSS instance of PF */ vsi->rss_table_size = (u16)cap->rss_table_size; if (vsi->type == ICE_VSI_CHNL) - vsi->rss_size = min_t(u16, vsi->num_rxq, - BIT(cap->rss_table_entry_width)); + vsi->rss_size = min_t(u16, vsi->num_rxq, max_rss_size); else vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; + max_rss_size); + vsi->rss_lut_type = ICE_LUT_PF; break; case ICE_VSI_SWITCHDEV_CTRL: - vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; - vsi->rss_size = min_t(u16, num_online_cpus(), - BIT(cap->rss_table_entry_width)); - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + vsi->rss_table_size = ICE_LUT_VSI_SIZE; + vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size); + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_VF: /* VF VSI will get a small RSS table. * For VSI_LUT, LUT size should be set to 64 bytes. */ - vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vsi->rss_table_size = ICE_LUT_VSI_SIZE; vsi->rss_size = ICE_MAX_RSS_QS_PER_VF; - vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + vsi->rss_lut_type = ICE_LUT_VSI; break; case ICE_VSI_LB: break; @@ -1228,6 +1228,17 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) } /** + * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not + * @vsi: VSI to check whether or not VLAN pruning is enabled. + * + * returns true if Rx VLAN pruning is enabled and false otherwise. + */ +static bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) +{ + return vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; +} + +/** * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured * @vsi_flags: VSI configuration flags @@ -1685,6 +1696,27 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) } /** + * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length + * @vsi: VSI + */ +static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) +{ + if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; + vsi->rx_buf_len = ICE_RXBUF_1664; +#if (PAGE_SIZE < 8192) + } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && + (vsi->netdev->mtu <= ETH_DATA_LEN)) { + vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; + vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; +#endif + } else { + vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; + vsi->rx_buf_len = ICE_RXBUF_3072; + } +} + +/** * ice_pf_state_is_nominal - checks the PF for nominal state * @pf: pointer to PF to check * @@ -1759,27 +1791,6 @@ void ice_update_eth_stats(struct ice_vsi *vsi) } /** - * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length - * @vsi: VSI - */ -void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) -{ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; - vsi->rx_buf_len = ICE_RXBUF_1664; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif - } else { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - vsi->rx_buf_len = ICE_RXBUF_3072; - } -} - -/** * ice_write_qrxflxp_cntxt - write/configure QRXFLXP_CNTXT register * @hw: HW pointer * @pf_q: index of the Rx queue in the PF's queue space @@ -2185,20 +2196,6 @@ bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi) return false; } -/** - * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not - * @vsi: VSI to check whether or not VLAN pruning is enabled. - * - * returns true if Rx VLAN pruning is enabled and false otherwise. - */ -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) -{ - if (!vsi) - return false; - - return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA); -} - static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) { if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { @@ -2944,21 +2941,6 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi) } /** - * ice_napi_del - Remove NAPI handler for the VSI - * @vsi: VSI for which NAPI handler is to be removed - */ -void ice_napi_del(struct ice_vsi *vsi) -{ - int v_idx; - - if (!vsi->netdev) - return; - - ice_for_each_q_vector(vsi, v_idx) - netif_napi_del(&vsi->q_vectors[v_idx]->napi); -} - -/** * ice_vsi_release - Delete a VSI and free its resources * @vsi: the VSI being removed * @@ -2972,39 +2954,12 @@ int ice_vsi_release(struct ice_vsi *vsi) return -ENODEV; pf = vsi->back; - /* do not unregister while driver is in the reset recovery pending - * state. Since reset/rebuild happens through PF service task workqueue, - * it's not a good idea to unregister netdev that is associated to the - * PF that is running the work queue items currently. This is done to - * avoid check_flush_dependency() warning on this wq - */ - if (vsi->netdev && !ice_is_reset_in_progress(pf->state) && - (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state))) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - - if (vsi->type == ICE_VSI_PF) - ice_devlink_destroy_pf_port(pf); - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); ice_vsi_close(vsi); ice_vsi_decfg(vsi); - if (vsi->netdev) { - if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - if (test_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state)) { - free_netdev(vsi->netdev); - vsi->netdev = NULL; - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - } - } - /* retain SW VSI data structure since it is needed to unregister and * free VSI netdev when PF is not in reset recovery pending state,\ * for ex: during rmmod. @@ -3997,7 +3952,7 @@ bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f) * @pf: pointer to the struct ice_pf instance * @f: feature enum to set */ -static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) { if (f < 0 || f >= ICE_F_MAX) return; @@ -4103,3 +4058,28 @@ void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx) { ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; } + +/** + * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit + * @vsi: pointer to VSI structure + * @set: set or unset the bit + */ +int +ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set) +{ + struct ice_vsi_ctx ctx = { + .info = vsi->info, + }; + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + if (set) + ctx.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + else + ctx.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_LOCAL_LB; + + if (ice_update_vsi(&vsi->back->hw, vsi->idx, &ctx, NULL)) + return -ENODEV; + + vsi->info = ctx.info; + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index e985766e6bb5..f24f5d1e6f9c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -76,8 +76,6 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); -bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi); - void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); @@ -93,8 +91,6 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); -void ice_napi_del(struct ice_vsi *vsi); - int ice_vsi_release(struct ice_vsi *vsi); void ice_vsi_close(struct ice_vsi *vsi); @@ -130,7 +126,6 @@ void ice_update_tx_ring_stats(struct ice_tx_ring *ring, u64 pkts, u64 bytes); void ice_update_rx_ring_stats(struct ice_rx_ring *ring, u64 pkts, u64 bytes); -void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl); void ice_write_itr(struct ice_ring_container *rc, u16 itr); void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); @@ -157,11 +152,13 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); +int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set); int ice_vsi_add_vlan_zero(struct ice_vsi *vsi); int ice_vsi_del_vlan_zero(struct ice_vsi *vsi); bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi); u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi); bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); +void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 93979ab18bc1..c8286adae946 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -64,6 +64,7 @@ struct device *ice_hw_to_dev(struct ice_hw *hw) } static struct workqueue_struct *ice_wq; +struct workqueue_struct *ice_lag_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; @@ -80,7 +81,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); -bool netif_is_ice(struct net_device *dev) +bool netif_is_ice(const struct net_device *dev) { return dev && (dev->netdev_ops == &ice_netdev_ops); } @@ -635,6 +636,11 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "reset_type 0x%x requested\n", reset_type); + if (pf->lag && pf->lag->bonded && reset_type == ICE_RESET_PFR) { + dev_dbg(dev, "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + ice_prepare_for_reset(pf, reset_type); /* trigger the reset */ @@ -718,8 +724,13 @@ static void ice_reset_subtask(struct ice_pf *pf) } /* No pending resets to finish processing. Check for new resets */ - if (test_bit(ICE_PFR_REQ, pf->state)) + if (test_bit(ICE_PFR_REQ, pf->state)) { reset_type = ICE_RESET_PFR; + if (pf->lag && pf->lag->bonded) { + dev_dbg(ice_pf_to_dev(pf), "PFR on a bonded interface, promoting to CORER\n"); + reset_type = ICE_RESET_CORER; + } + } if (test_bit(ICE_CORER_REQ, pf->state)) reset_type = ICE_RESET_CORER; if (test_bit(ICE_GLOBR_REQ, pf->state)) @@ -1239,64 +1250,63 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event) return status; } -enum ice_aq_task_state { - ICE_AQ_TASK_WAITING = 0, - ICE_AQ_TASK_COMPLETE, - ICE_AQ_TASK_CANCELED, -}; - -struct ice_aq_task { - struct hlist_node entry; +/** + * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware + * @pf: pointer to the PF private structure + * @task: intermediate helper storage and identifier for waiting + * @opcode: the opcode to wait for + * + * Prepares to wait for a specific AdminQ completion event on the ARQ for + * a given PF. Actual wait would be done by a call to ice_aq_wait_for_event(). + * + * Calls are separated to allow caller registering for event before sending + * the command, which mitigates a race between registering and FW responding. + * + * To obtain only the descriptor contents, pass an task->event with null + * msg_buf. If the complete data buffer is desired, allocate the + * task->event.msg_buf with enough space ahead of time. + */ +void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task, + u16 opcode) +{ + INIT_HLIST_NODE(&task->entry); + task->opcode = opcode; + task->state = ICE_AQ_TASK_WAITING; - u16 opcode; - struct ice_rq_event_info *event; - enum ice_aq_task_state state; -}; + spin_lock_bh(&pf->aq_wait_lock); + hlist_add_head(&task->entry, &pf->aq_wait_list); + spin_unlock_bh(&pf->aq_wait_lock); +} /** * ice_aq_wait_for_event - Wait for an AdminQ event from firmware * @pf: pointer to the PF private structure - * @opcode: the opcode to wait for + * @task: ptr prepared by ice_aq_prep_for_event() * @timeout: how long to wait, in jiffies - * @event: storage for the event info * * Waits for a specific AdminQ completion event on the ARQ for a given PF. The * current thread will be put to sleep until the specified event occurs or * until the given timeout is reached. * - * To obtain only the descriptor contents, pass an event without an allocated - * msg_buf. If the complete data buffer is desired, allocate the - * event->msg_buf with enough space ahead of time. - * * Returns: zero on success, or a negative error code on failure. */ -int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, - struct ice_rq_event_info *event) +int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task, + unsigned long timeout) { + enum ice_aq_task_state *state = &task->state; struct device *dev = ice_pf_to_dev(pf); - struct ice_aq_task *task; - unsigned long start; + unsigned long start = jiffies; long ret; int err; - task = kzalloc(sizeof(*task), GFP_KERNEL); - if (!task) - return -ENOMEM; - - INIT_HLIST_NODE(&task->entry); - task->opcode = opcode; - task->event = event; - task->state = ICE_AQ_TASK_WAITING; - - spin_lock_bh(&pf->aq_wait_lock); - hlist_add_head(&task->entry, &pf->aq_wait_list); - spin_unlock_bh(&pf->aq_wait_lock); - - start = jiffies; - - ret = wait_event_interruptible_timeout(pf->aq_wait_queue, task->state, + ret = wait_event_interruptible_timeout(pf->aq_wait_queue, + *state != ICE_AQ_TASK_WAITING, timeout); - switch (task->state) { + switch (*state) { + case ICE_AQ_TASK_NOT_PREPARED: + WARN(1, "call to %s without ice_aq_prep_for_event()", __func__); + err = -EINVAL; + break; case ICE_AQ_TASK_WAITING: err = ret < 0 ? ret : -ETIMEDOUT; break; @@ -1307,7 +1317,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, err = ret < 0 ? ret : 0; break; default: - WARN(1, "Unexpected AdminQ wait task state %u", task->state); + WARN(1, "Unexpected AdminQ wait task state %u", *state); err = -EINVAL; break; } @@ -1315,12 +1325,11 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, dev_dbg(dev, "Waited %u msecs (max %u msecs) for firmware response to op 0x%04x\n", jiffies_to_msecs(jiffies - start), jiffies_to_msecs(timeout), - opcode); + task->opcode); spin_lock_bh(&pf->aq_wait_lock); hlist_del(&task->entry); spin_unlock_bh(&pf->aq_wait_lock); - kfree(task); return err; } @@ -1346,23 +1355,26 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, static void ice_aq_check_events(struct ice_pf *pf, u16 opcode, struct ice_rq_event_info *event) { + struct ice_rq_event_info *task_ev; struct ice_aq_task *task; bool found = false; spin_lock_bh(&pf->aq_wait_lock); hlist_for_each_entry(task, &pf->aq_wait_list, entry) { - if (task->state || task->opcode != opcode) + if (task->state != ICE_AQ_TASK_WAITING) + continue; + if (task->opcode != opcode) continue; - memcpy(&task->event->desc, &event->desc, sizeof(event->desc)); - task->event->msg_len = event->msg_len; + task_ev = &task->event; + memcpy(&task_ev->desc, &event->desc, sizeof(event->desc)); + task_ev->msg_len = event->msg_len; /* Only copy the data buffer if a destination was set */ - if (task->event->msg_buf && - task->event->buf_len > event->buf_len) { - memcpy(task->event->msg_buf, event->msg_buf, + if (task_ev->msg_buf && task_ev->buf_len >= event->buf_len) { + memcpy(task_ev->msg_buf, event->msg_buf, event->buf_len); - task->event->buf_len = event->buf_len; + task_ev->buf_len = event->buf_len; } task->state = ICE_AQ_TASK_COMPLETE; @@ -3392,6 +3404,7 @@ static void ice_set_ops(struct ice_vsi *vsi) netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY | NETDEV_XDP_ACT_RX_SG; + netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD; } /** @@ -3794,6 +3807,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) static void ice_deinit_pf(struct ice_pf *pf) { ice_service_task_stop(pf); + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); @@ -3874,6 +3888,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); mutex_init(&pf->adev_mutex); + mutex_init(&pf->lag_mutex); INIT_HLIST_HEAD(&pf->aq_wait_list); spin_lock_init(&pf->aq_wait_lock); @@ -4430,9 +4445,9 @@ static int ice_start_eth(struct ice_vsi *vsi) if (err) return err; - rtnl_lock(); err = ice_vsi_open(vsi); - rtnl_unlock(); + if (err) + ice_fltr_remove_all(vsi); return err; } @@ -4506,6 +4521,31 @@ static void ice_deinit_eth(struct ice_pf *pf) ice_decfg_netdev(vsi); } +/** + * ice_wait_for_fw - wait for full FW readiness + * @hw: pointer to the hardware structure + * @timeout: milliseconds that can elapse before timing out + */ +static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) +{ + int fw_loading; + u32 elapsed = 0; + + while (elapsed <= timeout) { + fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; + + /* firmware was not yet loaded, we have to wait more */ + if (fw_loading) { + elapsed += 100; + msleep(100); + continue; + } + return 0; + } + + return -ETIMEDOUT; +} + static int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); @@ -4518,6 +4558,18 @@ static int ice_init_dev(struct ice_pf *pf) return err; } + /* Some cards require longer initialization times + * due to necessity of loading FW from an external source. + * This can take even half a minute. + */ + if (ice_is_pf_c827(hw)) { + err = ice_wait_for_fw(hw, 30000); + if (err) { + dev_err(dev, "ice_wait_for_fw timed out"); + return err; + } + } + ice_init_feature_support(pf); ice_request_fw(pf); @@ -4895,6 +4947,7 @@ int ice_load(struct ice_pf *pf) params = ice_vsi_to_params(vsi); params.flags = ICE_VSI_FLAG_INIT; + rtnl_lock(); err = ice_vsi_cfg(vsi, ¶ms); if (err) goto err_vsi_cfg; @@ -4902,6 +4955,7 @@ int ice_load(struct ice_pf *pf) err = ice_start_eth(ice_get_main_vsi(pf)); if (err) goto err_start_eth; + rtnl_unlock(); err = ice_init_rdma(pf); if (err) @@ -4916,9 +4970,11 @@ int ice_load(struct ice_pf *pf) err_init_rdma: ice_vsi_close(ice_get_main_vsi(pf)); + rtnl_lock(); err_start_eth: ice_vsi_decfg(ice_get_main_vsi(pf)); err_vsi_cfg: + rtnl_unlock(); ice_deinit_dev(pf); return err; } @@ -4931,8 +4987,10 @@ void ice_unload(struct ice_pf *pf) { ice_deinit_features(pf); ice_deinit_rdma(pf); + rtnl_lock(); ice_stop_eth(ice_get_main_vsi(pf)); ice_vsi_decfg(ice_get_main_vsi(pf)); + rtnl_unlock(); ice_deinit_dev(pf); } @@ -5564,7 +5622,7 @@ static struct pci_driver ice_driver = { */ static int __init ice_module_init(void) { - int status; + int status = -ENOMEM; pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); @@ -5572,15 +5630,27 @@ static int __init ice_module_init(void) ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); - return -ENOMEM; + return status; + } + + ice_lag_wq = alloc_ordered_workqueue("ice_lag_wq", 0); + if (!ice_lag_wq) { + pr_err("Failed to create LAG workqueue\n"); + goto err_dest_wq; } status = pci_register_driver(&ice_driver); if (status) { pr_err("failed to register PCI driver, err %d\n", status); - destroy_workqueue(ice_wq); + goto err_dest_lag_wq; } + return 0; + +err_dest_lag_wq: + destroy_workqueue(ice_lag_wq); +err_dest_wq: + destroy_workqueue(ice_wq); return status; } module_init(ice_module_init); @@ -5595,6 +5665,7 @@ static void __exit ice_module_exit(void) { pci_unregister_driver(&ice_driver); destroy_workqueue(ice_wq); + destroy_workqueue(ice_lag_wq); pr_info("module unloaded\n"); } module_exit(ice_module_exit); @@ -5697,7 +5768,7 @@ static void ice_set_rx_mode(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - if (!vsi) + if (!vsi || ice_is_switchdev_running(vsi->back)) return; /* Set the flags to synchronize filters @@ -5739,6 +5810,13 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) q_handle = vsi->tx_rings[queue_index]->q_handle; tc = ice_dcb_get_tc(vsi, queue_index); + vsi = ice_locate_vsi_using_queue(vsi, queue_index); + if (!vsi) { + netdev_err(netdev, "Invalid VSI for given queue %d\n", + queue_index); + return -EINVAL; + } + /* Set BW back to default, when user set maxrate to 0 */ if (!maxrate) status = ice_cfg_q_bw_dflt_lmt(vsi->port_info, vsi->idx, tc, @@ -6242,7 +6320,7 @@ static void ice_tx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile)); @@ -6262,7 +6340,7 @@ static void ice_rx_dim_work(struct work_struct *work) u16 itr; dim = container_of(work, struct dim, work); - rc = (struct ice_ring_container *)dim->priv; + rc = dim->priv; WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile)); @@ -7343,6 +7421,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) clear_bit(ICE_RESET_FAILED, pf->state); ice_plug_aux_dev(pf); + if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + ice_lag_rebuild(pf); return; err_vsi_rebuild: @@ -7872,10 +7952,10 @@ static int ice_validate_mqprio_qopt(struct ice_vsi *vsi, struct tc_mqprio_qopt_offload *mqprio_qopt) { - u64 sum_max_rate = 0, sum_min_rate = 0; int non_power_of_2_qcount = 0; struct ice_pf *pf = vsi->back; int max_rss_q_cnt = 0; + u64 sum_min_rate = 0; struct device *dev; int i, speed; u8 num_tc; @@ -7891,6 +7971,7 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, dev = ice_pf_to_dev(pf); vsi->ch_rss_size = 0; num_tc = mqprio_qopt->qopt.num_tc; + speed = ice_get_link_speed_kbps(vsi); for (i = 0; num_tc; i++) { int qcount = mqprio_qopt->qopt.count[i]; @@ -7931,7 +8012,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, */ max_rate = mqprio_qopt->max_rate[i]; max_rate = div_u64(max_rate, ICE_BW_KBPS_DIVISOR); - sum_max_rate += max_rate; /* min_rate is minimum guaranteed rate and it can't be zero */ min_rate = mqprio_qopt->min_rate[i]; @@ -7944,6 +8024,12 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, return -EINVAL; } + if (max_rate && max_rate > speed) { + dev_err(dev, "TC%d: max_rate(%llu Kbps) > link speed of %u Kbps\n", + i, max_rate, speed); + return -EINVAL; + } + iter_div_u64_rem(min_rate, ICE_MIN_BW_LIMIT, &rem); if (rem) { dev_err(dev, "TC%d: Min Rate not multiple of %u Kbps", @@ -7981,12 +8067,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi, (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) return -EINVAL; - speed = ice_get_link_speed_kbps(vsi); - if (sum_max_rate && sum_max_rate > (u64)speed) { - dev_err(dev, "Invalid max Tx rate(%llu) Kbps > speed(%u) Kbps specified\n", - sum_max_rate, speed); - return -EINVAL; - } if (sum_min_rate && sum_min_rate > (u64)speed) { dev_err(dev, "Invalid min Tx rate(%llu) Kbps > speed (%u) Kbps specified\n", sum_min_rate, speed); @@ -8800,6 +8880,7 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_pf *pf = np->vsi->back; + bool locked = false; int err; switch (type) { @@ -8809,10 +8890,32 @@ ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, ice_setup_tc_block_cb, np, np, true); case TC_SETUP_QDISC_MQPRIO: + if (ice_is_eswitch_mode_switchdev(pf)) { + netdev_err(netdev, "TC MQPRIO offload not supported, switchdev is enabled\n"); + return -EOPNOTSUPP; + } + + if (pf->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&pf->adev->dev); + locked = true; + if (pf->adev->dev.driver) { + netdev_err(netdev, "Cannot change qdisc when RDMA is active\n"); + err = -EBUSY; + goto adev_unlock; + } + } + /* setup traffic classifier for receive side */ mutex_lock(&pf->tc_mutex); err = ice_setup_tc_mqprio_qdisc(netdev, type_data); mutex_unlock(&pf->tc_mutex); + +adev_unlock: + if (locked) { + device_unlock(&pf->adev->dev); + mutex_unlock(&pf->adev_mutex); + } return err; default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 6a9364761165..f6f27361c3cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -287,6 +287,7 @@ struct ice_nvgre_hdr { * M = EVLAN (0x8100) - Outer L2 header has EVLAN (ethernet type 0x8100) * N = EVLAN (0x9100) - Outer L2 header has EVLAN (ethernet type 0x9100) */ +#define ICE_PKT_FROM_NETWORK BIT(3) #define ICE_PKT_VLAN_STAG BIT(12) #define ICE_PKT_VLAN_ITAG BIT(13) #define ICE_PKT_VLAN_EVLAN (BIT(14) | BIT(15)) @@ -392,10 +393,10 @@ enum ice_hw_metadata_offset { }; enum ice_pkt_flags { - ICE_PKT_FLAGS_VLAN = 0, - ICE_PKT_FLAGS_TUNNEL = 1, - ICE_PKT_FLAGS_TCP = 2, - ICE_PKT_FLAGS_ERROR = 3, + ICE_PKT_FLAGS_MDID20 = 0, + ICE_PKT_FLAGS_MDID21 = 1, + ICE_PKT_FLAGS_MDID22 = 2, + ICE_PKT_FLAGS_MDID23 = 3, }; struct ice_hw_metadata { diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index a38614d21ea8..f818dd215c05 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -131,6 +131,8 @@ static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) case READ_TIME: cmd_val |= GLTSYN_CMD_READ_TIME; break; + case ICE_PTP_NOP: + break; } wr32(hw, GLTSYN_CMD, cmd_val); @@ -293,7 +295,7 @@ static bool ice_is_40b_phy_reg_e822(u16 low_addr, u16 *high_addr) * * Read a PHY register for the given port over the device sideband queue. */ -int +static int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val) { struct ice_sbq_msg_input msg = {0}; @@ -370,7 +372,7 @@ ice_read_64b_phy_reg_e822(struct ice_hw *hw, u8 port, u16 low_addr, u64 *val) * * Write a PHY register for the given port over the device sideband queue. */ -int +static int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val) { struct ice_sbq_msg_input msg = {0}; @@ -1079,7 +1081,7 @@ exit_err: * * Negative adjustments are supported using 2s complement arithmetic. */ -int +static int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time) { u32 l_time, u_time; @@ -1226,18 +1228,18 @@ ice_ptp_read_port_capture(struct ice_hw *hw, u8 port, u64 *tx_ts, u64 *rx_ts) } /** - * ice_ptp_one_port_cmd - Prepare a single PHY port for a timer command + * ice_ptp_write_port_cmd_e822 - Prepare a single PHY port for a timer command * @hw: pointer to HW struct * @port: Port to which cmd has to be sent * @cmd: Command to be sent to the port * * Prepare the requested port for an upcoming timer sync command. * - * Note there is no equivalent of this operation on E810, as that device - * always handles all external PHYs internally. + * Do not use this function directly. If you want to configure exactly one + * port, use ice_ptp_one_port_cmd() instead. */ static int -ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) +ice_ptp_write_port_cmd_e822(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { u32 cmd_val, val; u8 tmr_idx; @@ -1261,6 +1263,8 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) case ADJ_TIME_AT_TIME: cmd_val |= PHY_CMD_ADJ_TIME_AT_TIME; break; + case ICE_PTP_NOP: + break; } /* Tx case */ @@ -1307,6 +1311,39 @@ ice_ptp_one_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) } /** + * ice_ptp_one_port_cmd - Prepare one port for a timer command + * @hw: pointer to the HW struct + * @configured_port: the port to configure with configured_cmd + * @configured_cmd: timer command to prepare on the configured_port + * + * Prepare the configured_port for the configured_cmd, and prepare all other + * ports for ICE_PTP_NOP. This causes the configured_port to execute the + * desired command while all other ports perform no operation. + */ +static int +ice_ptp_one_port_cmd(struct ice_hw *hw, u8 configured_port, + enum ice_ptp_tmr_cmd configured_cmd) +{ + u8 port; + + for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { + enum ice_ptp_tmr_cmd cmd; + int err; + + if (port == configured_port) + cmd = configured_cmd; + else + cmd = ICE_PTP_NOP; + + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); + if (err) + return err; + } + + return 0; +} + +/** * ice_ptp_port_cmd_e822 - Prepare all ports for a timer command * @hw: pointer to the HW struct * @cmd: timer command to prepare @@ -1322,7 +1359,7 @@ ice_ptp_port_cmd_e822(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) for (port = 0; port < ICE_NUM_EXTERNAL_PORTS; port++) { int err; - err = ice_ptp_one_port_cmd(hw, port, cmd); + err = ice_ptp_write_port_cmd_e822(hw, port, cmd); if (err) return err; } @@ -2252,6 +2289,9 @@ static int ice_sync_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) goto err_unlock; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + /* Issue the sync to activate the time adjustment */ ice_ptp_exec_tmr_cmd(hw); @@ -2372,6 +2412,9 @@ int ice_start_phy_timer_e822(struct ice_hw *hw, u8 port) if (err) return err; + /* Do not perform any action on the main timer */ + ice_ptp_src_cmd(hw, ICE_PTP_NOP); + ice_ptp_exec_tmr_cmd(hw); err = ice_read_phy_reg_e822(hw, port, P_REG_PS, &val); @@ -2847,6 +2890,8 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) case ADJ_TIME_AT_TIME: cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; break; + case ICE_PTP_NOP: + return 0; } /* Read, modify, write */ @@ -2869,6 +2914,185 @@ static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) return 0; } +/** + * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register + * @hw: pointer to the HW struct + * @port: the PHY port to read + * @tstamp_ready: contents of the Tx memory status register + * + * E810 devices do not use a Tx memory status register. Instead simply + * indicate that all timestamps are currently ready. + */ +static int +ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) +{ + *tstamp_ready = 0xFFFFFFFFFFFFFFFF; + return 0; +} + +/* E810T SMA functions + * + * The following functions operate specifically on E810T hardware and are used + * to access the extended GPIOs available. + */ + +/** + * ice_get_pca9575_handle + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value + */ +static int +ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int status; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + + /* If handle was not detected read it from the netlist */ + cmd = &desc.params.get_link_topo; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + + /* Set node type to GPIO controller */ + cmd->addr.topo_params.node_type_ctx = + (ICE_AQC_LINK_TOPO_NODE_TYPE_M & + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -EOPNOTSUPP; + + cmd->addr.topo_params.index = idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (status) + return -EOPNOTSUPP; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -EOPNOTSUPP; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: pointer to data to be read from the GPIO controller + * + * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the + * PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + *data = 0; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + &pin, NULL); + if (status) + break; + *data |= (u8)(!pin) << i; + } + + return status; +} + +/** + * ice_write_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: data to be written to the GPIO controller + * + * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 + * of the PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + pin = !(data & (1 << i)); + status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + pin, NULL); + if (status) + break; + } + + return status; +} + +/** + * ice_read_pca9575_reg_e810t + * @hw: pointer to the hw struct + * @offset: GPIO controller register offset + * @data: pointer to data to be read from the GPIO controller + * + * Read the register from the GPIO controller + */ +int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data) +{ + struct ice_aqc_link_topo_addr link_topo; + __le16 addr; + u16 handle; + int err; + + memset(&link_topo, 0, sizeof(link_topo)); + + err = ice_get_pca9575_handle(hw, &handle); + if (err) + return err; + + link_topo.handle = cpu_to_le16(handle); + link_topo.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); + + addr = cpu_to_le16((u16)offset); + + return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); +} + /* Device agnostic functions * * The following functions implement shared behavior common to both E822 and @@ -3130,204 +3354,6 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) } /** - * ice_get_phy_tx_tstamp_ready_e810 - Read Tx memory status register - * @hw: pointer to the HW struct - * @port: the PHY port to read - * @tstamp_ready: contents of the Tx memory status register - * - * E810 devices do not use a Tx memory status register. Instead simply - * indicate that all timestamps are currently ready. - */ -static int -ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) -{ - *tstamp_ready = 0xFFFFFFFFFFFFFFFF; - return 0; -} - -/* E810T SMA functions - * - * The following functions operate specifically on E810T hardware and are used - * to access the extended GPIOs available. - */ - -/** - * ice_get_pca9575_handle - * @hw: pointer to the hw struct - * @pca9575_handle: GPIO controller's handle - * - * Find and return the GPIO controller's handle in the netlist. - * When found - the value will be cached in the hw structure and following calls - * will return cached value - */ -static int -ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) -{ - struct ice_aqc_get_link_topo *cmd; - struct ice_aq_desc desc; - int status; - u8 idx; - - /* If handle was read previously return cached value */ - if (hw->io_expander_handle) { - *pca9575_handle = hw->io_expander_handle; - return 0; - } - - /* If handle was not detected read it from the netlist */ - cmd = &desc.params.get_link_topo; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); - - /* Set node type to GPIO controller */ - cmd->addr.topo_params.node_type_ctx = - (ICE_AQC_LINK_TOPO_NODE_TYPE_M & - ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); - -#define SW_PCA9575_SFP_TOPO_IDX 2 -#define SW_PCA9575_QSFP_TOPO_IDX 1 - - /* Check if the SW IO expander controlling SMA exists in the netlist. */ - if (hw->device_id == ICE_DEV_ID_E810C_SFP) - idx = SW_PCA9575_SFP_TOPO_IDX; - else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) - idx = SW_PCA9575_QSFP_TOPO_IDX; - else - return -EOPNOTSUPP; - - cmd->addr.topo_params.index = idx; - - status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); - if (status) - return -EOPNOTSUPP; - - /* Verify if we found the right IO expander type */ - if (desc.params.get_link_topo.node_part_num != - ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) - return -EOPNOTSUPP; - - /* If present save the handle and return it */ - hw->io_expander_handle = - le16_to_cpu(desc.params.get_link_topo.addr.handle); - *pca9575_handle = hw->io_expander_handle; - - return 0; -} - -/** - * ice_read_sma_ctrl_e810t - * @hw: pointer to the hw struct - * @data: pointer to data to be read from the GPIO controller - * - * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the - * PCA9575 expander, so only bits 3-7 in data are valid. - */ -int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) -{ - int status; - u16 handle; - u8 i; - - status = ice_get_pca9575_handle(hw, &handle); - if (status) - return status; - - *data = 0; - - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { - bool pin; - - status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, - &pin, NULL); - if (status) - break; - *data |= (u8)(!pin) << i; - } - - return status; -} - -/** - * ice_write_sma_ctrl_e810t - * @hw: pointer to the hw struct - * @data: data to be written to the GPIO controller - * - * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 - * of the PCA9575 expander, so only bits 3-7 in data are valid. - */ -int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) -{ - int status; - u16 handle; - u8 i; - - status = ice_get_pca9575_handle(hw, &handle); - if (status) - return status; - - for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { - bool pin; - - pin = !(data & (1 << i)); - status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, - pin, NULL); - if (status) - break; - } - - return status; -} - -/** - * ice_read_pca9575_reg_e810t - * @hw: pointer to the hw struct - * @offset: GPIO controller register offset - * @data: pointer to data to be read from the GPIO controller - * - * Read the register from the GPIO controller - */ -int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data) -{ - struct ice_aqc_link_topo_addr link_topo; - __le16 addr; - u16 handle; - int err; - - memset(&link_topo, 0, sizeof(link_topo)); - - err = ice_get_pca9575_handle(hw, &handle); - if (err) - return err; - - link_topo.handle = cpu_to_le16(handle); - link_topo.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, - ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); - - addr = cpu_to_le16((u16)offset); - - return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); -} - -/** - * ice_is_pca9575_present - * @hw: pointer to the hw struct - * - * Check if the SW IO expander is present in the netlist - */ -bool ice_is_pca9575_present(struct ice_hw *hw) -{ - u16 handle = 0; - int status; - - if (!ice_is_e810t(hw)) - return false; - - status = ice_get_pca9575_handle(hw, &handle); - - return !status && handle; -} - -/** * ice_ptp_reset_ts_memory - Reset timestamp memory for all blocks * @hw: pointer to the HW struct */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 3b68cb91bd81..9aa10b0426fd 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -9,7 +9,8 @@ enum ice_ptp_tmr_cmd { INIT_INCVAL, ADJ_TIME, ADJ_TIME_AT_TIME, - READ_TIME + READ_TIME, + ICE_PTP_NOP, }; enum ice_ptp_serdes { @@ -112,6 +113,9 @@ struct ice_cgu_pll_params_e822 { extern const struct ice_cgu_pll_params_e822 e822_cgu_params[NUM_ICE_TIME_REF_FREQ]; +#define E810C_QSFP_C827_0_HANDLE 2 +#define E810C_QSFP_C827_1_HANDLE 3 + /* Table of constants related to possible TIME_REF sources */ extern const struct ice_time_ref_info_e822 e822_time_ref[NUM_ICE_TIME_REF_FREQ]; @@ -138,11 +142,8 @@ int ice_ptp_init_phc(struct ice_hw *hw); int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready); /* E822 family functions */ -int ice_read_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 *val); -int ice_write_phy_reg_e822(struct ice_hw *hw, u8 port, u16 offset, u32 val); int ice_read_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 *val); int ice_write_quad_reg_e822(struct ice_hw *hw, u8 quad, u16 offset, u32 val); -int ice_ptp_prep_port_adj_e822(struct ice_hw *hw, u8 port, s64 time); void ice_ptp_reset_ts_memory_quad_e822(struct ice_hw *hw, u8 quad); /** @@ -196,7 +197,6 @@ int ice_ptp_init_phy_e810(struct ice_hw *hw); int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data); int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data); -bool ice_is_pca9575_present(struct ice_hw *hw); #define PFTSYN_SEM_BYTES 4 diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index e30e12321abd..c686ac0935eb 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -254,7 +254,7 @@ static const struct net_device_ops ice_repr_netdev_ops = { * ice_is_port_repr_netdev - Check if a given netdevice is a port representor netdev * @netdev: pointer to netdev */ -bool ice_is_port_repr_netdev(struct net_device *netdev) +bool ice_is_port_repr_netdev(const struct net_device *netdev) { return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops); } diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index 9c2a6f496b3b..e1ee2d2c1d2d 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -12,6 +12,7 @@ struct ice_repr { struct ice_q_vector *q_vector; struct net_device *netdev; struct metadata_dst *dst; + struct ice_esw_br_port *br_port; #ifdef CONFIG_ICE_SWITCHDEV /* info about slow path rule */ struct ice_rule_query_data sp_rule; @@ -27,5 +28,5 @@ void ice_repr_stop_tx_queues(struct ice_repr *repr); void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi); struct ice_repr *ice_netdev_to_repr(struct net_device *netdev); -bool ice_is_port_repr_netdev(struct net_device *netdev); +bool ice_is_port_repr_netdev(const struct net_device *netdev); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index b664d60fd037..c0533d7b66b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -447,7 +447,7 @@ ice_aq_cfg_sched_elems(struct ice_hw *hw, u16 elems_req, * * Move scheduling elements (0x0408) */ -static int +int ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, struct ice_aqc_move_elem *buf, u16 buf_size, u16 *grps_movd, struct ice_sq_cd *cd) @@ -526,7 +526,7 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size, * * This function suspends or resumes HW nodes */ -static int +int ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, bool suspend) { @@ -569,18 +569,24 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) { struct ice_vsi_ctx *vsi_ctx; struct ice_q_ctx *q_ctx; + u16 idx; vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) return -EINVAL; /* allocate LAN queue contexts */ if (!vsi_ctx->lan_q_ctx[tc]) { - vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), - new_numqs, - sizeof(*q_ctx), - GFP_KERNEL); - if (!vsi_ctx->lan_q_ctx[tc]) + q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, + sizeof(*q_ctx), GFP_KERNEL); + if (!q_ctx) return -ENOMEM; + + for (idx = 0; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; return 0; } @@ -592,9 +598,16 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) sizeof(*q_ctx), GFP_KERNEL); if (!q_ctx) return -ENOMEM; + memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc], prev_num * sizeof(*q_ctx)); devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]); + + for (idx = prev_num; idx < new_numqs; idx++) { + q_ctx[idx].q_handle = ICE_INVAL_Q_HANDLE; + q_ctx[idx].q_teid = ICE_INVAL_TEID; + } + vsi_ctx->lan_q_ctx[tc] = q_ctx; vsi_ctx->num_lan_q_entries[tc] = new_numqs; } @@ -1044,7 +1057,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, * * This function add nodes to a given layer. */ -static int +int ice_sched_add_nodes_to_layer(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, @@ -1119,7 +1132,7 @@ static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw) * * This function returns the current VSI layer number */ -static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) +u8 ice_sched_get_vsi_layer(struct ice_hw *hw) { /* Num Layers VSI layer * 9 6 @@ -1142,7 +1155,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) * * This function returns the current aggregator layer number */ -static u8 ice_sched_get_agg_layer(struct ice_hw *hw) +u8 ice_sched_get_agg_layer(struct ice_hw *hw) { /* Num Layers aggregator layer * 9 4 @@ -1577,7 +1590,7 @@ ice_sched_get_vsi_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, * This function retrieves an aggregator node for a given aggregator ID from * a given TC branch */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, u32 agg_id) { @@ -2139,7 +2152,7 @@ ice_get_agg_info(struct ice_hw *hw, u32 agg_id) * This function walks through the aggregator subtree to find a free parent * node */ -static struct ice_sched_node * +struct ice_sched_node * ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, u16 *num_nodes) { @@ -3958,7 +3971,7 @@ ice_sched_get_node_by_id_type(struct ice_port_info *pi, u32 id, * This function sets BW limit of VSI or Aggregator scheduling node * based on TC information from passed in argument BW. */ -int +static int ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, enum ice_agg_type agg_type, u8 tc, enum ice_rl_type rl_type, u32 bw) diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 9c100747445a..0055d9330c07 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -141,13 +141,30 @@ ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, int ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_rl_type rl_type); -int -ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, - enum ice_agg_type agg_type, u8 tc, - enum ice_rl_type rl_type, u32 bw); int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes); +int +ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, + bool suspend); +struct ice_sched_node * +ice_sched_get_agg_node(struct ice_port_info *pi, struct ice_sched_node *tc_node, + u32 agg_id); +u8 ice_sched_get_agg_layer(struct ice_hw *hw); +u8 ice_sched_get_vsi_layer(struct ice_hw *hw); +struct ice_sched_node * +ice_sched_get_free_vsi_parent(struct ice_hw *hw, struct ice_sched_node *node, + u16 *num_nodes); +int +ice_sched_add_nodes_to_layer(struct ice_port_info *pi, + struct ice_sched_node *tc_node, + struct ice_sched_node *parent, u8 layer, + u16 num_nodes, u32 *first_node_teid, + u16 *num_nodes_added); void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw); void ice_sched_replay_agg(struct ice_hw *hw); +int +ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, + struct ice_aqc_move_elem *buf, u16 buf_size, + u16 *grps_movd, struct ice_sq_cd *cd); int ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle); int ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 1f66914c7a20..31314e7540f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1131,7 +1131,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1246,7 +1246,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1300,7 +1300,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; } - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; @@ -1613,7 +1613,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_reset(vf); + ret = ice_check_vf_ready_for_cfg(vf); if (ret) goto out_put_vf; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 6db4ca7978cb..2f77b684ff76 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -20,12 +20,11 @@ * byte 0 = 0x2: to identify it as locally administered DA MAC * byte 6 = 0x2: to identify it as locally administered SA MAC * byte 12 = 0x81 & byte 13 = 0x00: - * In case of VLAN filter first two bytes defines ether type (0x8100) - * and remaining two bytes are placeholder for programming a given VLAN ID - * In case of Ether type filter it is treated as header without VLAN tag - * and byte 12 and 13 is used to program a given Ether type instead + * In case of VLAN filter first two bytes defines ether type (0x8100) + * and remaining two bytes are placeholder for programming a given VLAN ID + * In case of Ether type filter it is treated as header without VLAN tag + * and byte 12 and 13 is used to program a given Ether type instead */ -#define DUMMY_ETH_HDR_LEN 16 static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, 0x2, 0, 0, 0, 0, 0, 0x81, 0, 0, 0}; @@ -1369,14 +1368,6 @@ static const struct ice_dummy_pkt_profile ice_dummy_pkt_profiles[] = { ICE_PKT_PROFILE(tcp, 0), }; -#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) -#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) -#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ - ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) -#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) -#define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) - /* this is a recipe to profile association bitmap */ static DECLARE_BITMAP(recipe_to_profile[ICE_MAX_NUM_RECIPES], ICE_MAX_NUM_PROFILES); @@ -1841,8 +1832,13 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_DFLT) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { - sw_buf->res_type = - cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); + if (opc == ice_aqc_opc_alloc_res) + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE | + ICE_AQC_RES_TYPE_FLAG_SHARED); + else + sw_buf->res_type = + cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); } else { status = -EINVAL; goto ice_aq_alloc_free_vsi_list_exit; @@ -1851,7 +1847,7 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, if (opc == ice_aqc_opc_free_res) sw_buf->elem[0].e.sw_resp = cpu_to_le16(*vsi_list_id); - status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, opc, NULL); + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, opc); if (status) goto ice_aq_alloc_free_vsi_list_exit; @@ -1910,7 +1906,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, * * Add(0x0290) */ -static int +int ice_aq_add_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 num_recipes, struct ice_sq_cd *cd) @@ -1947,7 +1943,7 @@ ice_aq_add_recipe(struct ice_hw *hw, * The caller must supply enough space in s_recipe_list to hold all possible * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES. */ -static int +int ice_aq_get_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd) @@ -2040,7 +2036,7 @@ error_out: * @cd: pointer to command details structure or NULL * Recipe to profile association (0x0291) */ -static int +int ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2066,7 +2062,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @cd: pointer to command details structure or NULL * Associate profile ID with given recipe (0x0293) */ -static int +int ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -2090,7 +2086,7 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @hw: pointer to the hardware structure * @rid: recipe ID returned as response to AQ call */ -static int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { struct ice_aqc_alloc_free_res_elem *sw_buf; u16 buf_len; @@ -2105,8 +2101,8 @@ static int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE << ICE_AQC_RES_TYPE_S) | ICE_AQC_RES_TYPE_FLAG_SHARED); - status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, sw_buf, buf_len, + ice_aqc_opc_alloc_res); if (!status) *rid = le16_to_cpu(sw_buf->elem[0].e.sw_resp); kfree(sw_buf); @@ -2272,6 +2268,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, /* Propagate some data to the recipe database */ recps[idx].is_root = !!is_root; recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + recps[idx].need_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl & + ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS); if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) { recps[idx].chain_idx = root_bufs.content.result_indx & @@ -2460,6 +2460,15 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) } /** + * ice_fill_eth_hdr - helper to copy dummy_eth_hdr into supplied buffer + * @eth_hdr: pointer to buffer to populate + */ +void ice_fill_eth_hdr(u8 *eth_hdr) +{ + memcpy(eth_hdr, dummy_eth_header, DUMMY_ETH_HDR_LEN); +} + +/** * ice_fill_sw_rule - Helper function to fill switch rule structure * @hw: pointer to the hardware structure * @f_info: entry containing packet forwarding information @@ -3118,7 +3127,7 @@ ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) * handle element. This can be extended further to search VSI list with more * than 1 vsi_count. Returns pointer to VSI list entry if found. */ -static struct ice_vsi_list_map_info * +struct ice_vsi_list_map_info * ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, u16 *vsi_list_id) { @@ -3129,7 +3138,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, list_head = &sw->recp_list[recp_id].filt_rules; list_for_each_entry(list_itr, list_head, list_entry) { - if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) { + if (list_itr->vsi_list_info) { map_info = list_itr->vsi_list_info; if (test_bit(vsi_handle, map_info->vsi_map)) { *vsi_list_id = map_info->vsi_list_id; @@ -3400,54 +3409,6 @@ exit: } /** - * ice_mac_fltr_exist - does this MAC filter exist for given VSI - * @hw: pointer to the hardware structure - * @mac: MAC address to be checked (for MAC filter) - * @vsi_handle: check MAC filter for this VSI - */ -bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle) -{ - struct ice_fltr_mgmt_list_entry *entry; - struct list_head *rule_head; - struct ice_switch_info *sw; - struct mutex *rule_lock; /* Lock to protect filter rule list */ - u16 hw_vsi_id; - - if (!ice_is_vsi_valid(hw, vsi_handle)) - return false; - - hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - sw = hw->switch_info; - rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; - if (!rule_head) - return false; - - rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; - mutex_lock(rule_lock); - list_for_each_entry(entry, rule_head, list_entry) { - struct ice_fltr_info *f_info = &entry->fltr_info; - u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - - if (is_zero_ether_addr(mac_addr)) - continue; - - if (f_info->flag != ICE_FLTR_TX || - f_info->src_id != ICE_SRC_ID_VSI || - f_info->lkup_type != ICE_SW_LKUP_MAC || - f_info->fltr_act != ICE_FWD_TO_VSI || - hw_vsi_id != f_info->fwd_id.hw_vsi_id) - continue; - - if (ether_addr_equal(mac, mac_addr)) { - mutex_unlock(rule_lock); - return true; - } - } - mutex_unlock(rule_lock); - return false; -} - -/** * ice_vlan_fltr_exist - does this VLAN filter exist for given VSI * @hw: pointer to the hardware structure * @vlan_id: VLAN ID @@ -4487,8 +4448,7 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & ICE_AQC_RES_TYPE_M) | alloc_shared); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_alloc_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_alloc_res); if (status) goto exit; @@ -4526,8 +4486,7 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, ICE_AQC_RES_TYPE_M) | alloc_shared); buf->elem[0].e.sw_resp = cpu_to_le16(counter_id); - status = ice_aq_alloc_free_res(hw, 1, buf, buf_len, - ice_aqc_opc_free_res, NULL); + status = ice_aq_alloc_free_res(hw, buf, buf_len, ice_aqc_opc_free_res); if (status) ice_debug(hw, ICE_DBG_SW, "counter resource could not be freed\n"); @@ -4540,6 +4499,45 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, .offs = {__VA_ARGS__}, \ } +/** + * ice_share_res - set a resource as shared or dedicated + * @hw: hw struct of original owner of resource + * @type: resource type + * @shared: is the resource being set to shared + * @res_id: resource id (descriptor) + */ +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id) +{ + struct ice_aqc_alloc_free_res_elem *buf; + u16 buf_len; + int status; + + buf_len = struct_size(buf, elem, 1); + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + buf->num_elems = cpu_to_le16(1); + if (shared) + buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & + ICE_AQC_RES_TYPE_M) | + ICE_AQC_RES_TYPE_FLAG_SHARED); + else + buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & + ICE_AQC_RES_TYPE_M) & + ~ICE_AQC_RES_TYPE_FLAG_SHARED); + + buf->elem[0].e.sw_resp = cpu_to_le16(res_id); + status = ice_aq_alloc_free_res(hw, buf, buf_len, + ice_aqc_opc_share_res); + if (status) + ice_debug(hw, ICE_DBG_SW, "Could not set resource type %u id %u to %s\n", + type, res_id, shared ? "SHARED" : "DEDICATED"); + + kfree(buf); + return status; +} + /* This is mapping table entry that maps every word within a given protocol * structure to the real byte offset as per the specification of that * protocol header. @@ -4613,13 +4611,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * ice_find_recp - find a recipe * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match - * @tun_type: type of recipe tunnel + * @rinfo: information regarding the rule e.g. priority and action info * * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. */ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, - enum ice_sw_tunnel_type tun_type) + const struct ice_adv_rule_info *rinfo) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -4680,9 +4678,12 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, } /* If for "i"th recipe the found was never set to false * then it means we found our match - * Also tun type of recipe needs to be checked + * Also tun type and *_pass_l2 of recipe needs to be + * checked */ - if (found && recp[i].tun_type == tun_type) + if (found && recp[i].tun_type == rinfo->tun_type && + recp[i].need_pass_l2 == rinfo->need_pass_l2 && + recp[i].allow_pass_l2 == rinfo->allow_pass_l2) return i; /* Return the recipe ID */ } } @@ -4952,6 +4953,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, unsigned long *profiles) { DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_content *content; struct ice_aqc_recipe_data_elem *tmp; struct ice_aqc_recipe_data_elem *buf; struct ice_recp_grp_entry *entry; @@ -5012,6 +5014,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + /* Clear the result index of the located recipe, as this will be * updated, if needed, later in the recipe creation process. */ @@ -5022,26 +5026,24 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, /* if the recipe is a non-root recipe RID should be programmed * as 0 for the rules to be applied correctly. */ - buf[recps].content.rid = 0; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + content->rid = 0; + memset(&content->lkup_indx, 0, + sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); /* Setup lkup_indx 1..4 to INVALID/ignore and set the mask * to be 0 */ for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = 0x80; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = 0x80; + content->mask[i] = 0; } for (i = 0; i < entry->r_group.n_val_pairs; i++) { - buf[recps].content.lkup_indx[i + 1] = entry->fv_idx[i]; - buf[recps].content.mask[i + 1] = - cpu_to_le16(entry->fv_mask[i]); + content->lkup_indx[i + 1] = entry->fv_idx[i]; + content->mask[i + 1] = cpu_to_le16(entry->fv_mask[i]); } if (rm->n_grp_count > 1) { @@ -5055,7 +5057,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, } entry->chain_idx = chain_idx; - buf[recps].content.result_indx = + content->result_indx = ICE_AQ_RECIPE_RESULT_EN | ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & ICE_AQ_RECIPE_RESULT_DATA_M); @@ -5069,7 +5071,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, ICE_MAX_NUM_RECIPES); set_bit(buf[recps].recipe_indx, (unsigned long *)buf[recps].recipe_bitmap); - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; + + if (rm->need_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_NEED_PASS_L2; + + if (rm->allow_pass_l2) + content->act_ctrl |= ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2; recps++; } @@ -5107,9 +5115,11 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (status) goto err_unroll; + content = &buf[recps].content; + buf[recps].recipe_indx = (u8)rid; - buf[recps].content.rid = (u8)rid; - buf[recps].content.rid |= ICE_AQ_RECIPE_ID_IS_ROOT; + content->rid = (u8)rid; + content->rid |= ICE_AQ_RECIPE_ID_IS_ROOT; /* the new entry created should also be part of rg_list to * make sure we have complete recipe */ @@ -5121,16 +5131,13 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, goto err_unroll; } last_chain_entry->rid = rid; - memset(&buf[recps].content.lkup_indx, 0, - sizeof(buf[recps].content.lkup_indx)); + memset(&content->lkup_indx, 0, sizeof(content->lkup_indx)); /* All recipes use look-up index 0 to match switch ID. */ - buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; - buf[recps].content.mask[0] = - cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + content->lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + content->mask[0] = cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { - buf[recps].content.lkup_indx[i] = - ICE_AQ_RECIPE_LKUP_IGNORE; - buf[recps].content.mask[i] = 0; + content->lkup_indx[i] = ICE_AQ_RECIPE_LKUP_IGNORE; + content->mask[i] = 0; } i = 1; @@ -5142,8 +5149,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, last_chain_entry->chain_idx = ICE_INVAL_CHAIN_IND; list_for_each_entry(entry, &rm->rg_list, l_entry) { last_chain_entry->fv_idx[i] = entry->chain_idx; - buf[recps].content.lkup_indx[i] = entry->chain_idx; - buf[recps].content.mask[i++] = cpu_to_le16(0xFFFF); + content->lkup_indx[i] = entry->chain_idx; + content->mask[i++] = cpu_to_le16(0xFFFF); set_bit(entry->rid, rm->r_bitmap); } list_add(&last_chain_entry->l_entry, &rm->rg_list); @@ -5155,7 +5162,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, status = -EINVAL; goto err_unroll; } - buf[recps].content.act_ctrl_fwd_priority = rm->priority; + content->act_ctrl_fwd_priority = rm->priority; recps++; rm->root_rid = (u8)rid; @@ -5220,6 +5227,8 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, recp->priority = buf[buf_idx].content.act_ctrl_fwd_priority; recp->n_grp_count = rm->n_grp_count; recp->tun_type = rm->tun_type; + recp->need_pass_l2 = rm->need_pass_l2; + recp->allow_pass_l2 = rm->allow_pass_l2; recp->recp_created = true; } rm->root_buf = buf; @@ -5388,6 +5397,9 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, /* set the recipe priority if specified */ rm->priority = (u8)rinfo->priority; + rm->need_pass_l2 = rinfo->need_pass_l2; + rm->allow_pass_l2 = rinfo->allow_pass_l2; + /* Find offsets from the field vector. Pick the first one for all the * recipes. */ @@ -5403,7 +5415,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } /* Look for a recipe which matches our requested fv / mask list */ - *rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type); + *rid = ice_find_recp(hw, lkup_exts, rinfo); if (*rid < ICE_MAX_NUM_RECIPES) /* Success if found a recipe that match the existing criteria */ goto err_unroll; @@ -5839,7 +5851,9 @@ static bool ice_rules_equal(const struct ice_adv_rule_info *first, return first->sw_act.flag == second->sw_act.flag && first->tun_type == second->tun_type && first->vlan_type == second->vlan_type && - first->src_vsi == second->src_vsi; + first->src_vsi == second->src_vsi && + first->need_pass_l2 == second->need_pass_l2 && + first->allow_pass_l2 == second->allow_pass_l2; } /** @@ -5994,14 +6008,21 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup) { lkup->type = ICE_HW_METADATA; - lkup->m_u.metadata.flags[ICE_PKT_FLAGS_TUNNEL] = + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID21] |= cpu_to_be16(ICE_PKT_TUNNEL_MASK); } +void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup) +{ + lkup->type = ICE_HW_METADATA; + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |= + cpu_to_be16(ICE_PKT_FROM_NETWORK); +} + void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup) { lkup->type = ICE_HW_METADATA; - lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] = + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_MDID20] |= cpu_to_be16(ICE_PKT_VLAN_MASK); } @@ -6078,7 +6099,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (!(rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || - rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) { + rinfo->sw_act.fltr_act == ICE_DROP_PACKET || + rinfo->sw_act.fltr_act == ICE_NOP)) { status = -EIO; goto free_pkt_profile; } @@ -6089,7 +6111,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, goto free_pkt_profile; } - if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || + rinfo->sw_act.fltr_act == ICE_NOP) rinfo->sw_act.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); @@ -6159,6 +6182,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | ICE_SINGLE_ACT_VALID_BIT; break; + case ICE_NOP: + act |= FIELD_PREP(ICE_SINGLE_ACT_VSI_ID_M, + rinfo->sw_act.fwd_id.hw_vsi_id); + act &= ~ICE_SINGLE_ACT_VALID_BIT; + break; default: status = -EIO; goto err_ice_add_adv_rule; @@ -6439,7 +6467,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, return -EIO; } - rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type); + rid = ice_find_recp(hw, &lkup_exts, rinfo); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) return -EINVAL; @@ -6533,59 +6561,6 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw, } /** - * ice_rem_adv_rule_for_vsi - removes existing advanced switch rules for a - * given VSI handle - * @hw: pointer to the hardware structure - * @vsi_handle: VSI handle for which we are supposed to remove all the rules. - * - * This function is used to remove all the rules for a given VSI and as soon - * as removing a rule fails, it will return immediately with the error code, - * else it will return success. - */ -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle) -{ - struct ice_adv_fltr_mgmt_list_entry *list_itr, *tmp_entry; - struct ice_vsi_list_map_info *map_info; - struct ice_adv_rule_info rinfo; - struct list_head *list_head; - struct ice_switch_info *sw; - int status; - u8 rid; - - sw = hw->switch_info; - for (rid = 0; rid < ICE_MAX_NUM_RECIPES; rid++) { - if (!sw->recp_list[rid].recp_created) - continue; - if (!sw->recp_list[rid].adv_rule) - continue; - - list_head = &sw->recp_list[rid].filt_rules; - list_for_each_entry_safe(list_itr, tmp_entry, list_head, - list_entry) { - rinfo = list_itr->rule_info; - - if (rinfo.sw_act.fltr_act == ICE_FWD_TO_VSI_LIST) { - map_info = list_itr->vsi_list_info; - if (!map_info) - continue; - - if (!test_bit(vsi_handle, map_info->vsi_map)) - continue; - } else if (rinfo.sw_act.vsi_handle != vsi_handle) { - continue; - } - - rinfo.sw_act.vsi_handle = vsi_handle; - status = ice_rem_adv_rule(hw, list_itr->lkups, - list_itr->lkups_cnt, &rinfo); - if (status) - return status; - } - } - return 0; -} - -/** * ice_replay_vsi_adv_rule - Replay advanced rule for requested VSI * @hw: pointer to the hardware structure * @vsi_handle: driver VSI handle diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index c84b56fe84a5..db7e501b7e0a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -22,6 +22,16 @@ #define ICE_PROFID_IPV6_GTPU_TEID 46 #define ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER 70 +#define ICE_SW_RULE_VSI_LIST_SIZE(s, n) struct_size((s), vsi, (n)) +#define ICE_SW_RULE_RX_TX_HDR_SIZE(s, l) struct_size((s), hdr_data, (l)) +#define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), DUMMY_ETH_HDR_LEN) +#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE(s) \ + ICE_SW_RULE_RX_TX_HDR_SIZE((s), 0) +#define ICE_SW_RULE_LG_ACT_SIZE(s, n) struct_size((s), act, (n)) + +#define DUMMY_ETH_HDR_LEN 16 + /* VSI context structure for add/get/update/free operations */ struct ice_vsi_ctx { u16 vsi_num; @@ -191,6 +201,8 @@ struct ice_adv_rule_info { u16 vlan_type; u16 fltr_rule_id; u32 priority; + u16 need_pass_l2:1; + u16 allow_pass_l2:1; u16 src_vsi; struct ice_sw_act_ctrl sw_act; struct ice_adv_rule_flags_info flags_info; @@ -254,6 +266,9 @@ struct ice_sw_recipe { */ u8 priority; + u8 need_pass_l2:1; + u8 allow_pass_l2:1; + struct list_head rg_list; /* AQ buffer associated with this recipe */ @@ -340,9 +355,11 @@ ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); +int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id); /* Switch/bridge related commands */ void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup); +void ice_rule_add_direction_metadata(struct ice_adv_lkup_elem *lkup); void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup); void ice_rule_add_src_vsi_metadata(struct ice_adv_lkup_elem *lkup); int @@ -354,7 +371,6 @@ int ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); int ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); int ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); int ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); -bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle); bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle); int ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list); int ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); @@ -379,7 +395,6 @@ int ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc); -int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); int ice_rem_adv_rule_by_id(struct ice_hw *hw, struct ice_rule_query_data *remove_entry); @@ -389,6 +404,7 @@ u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); int ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); +void ice_fill_eth_hdr(u8 *eth_hdr); int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, @@ -397,4 +413,21 @@ int ice_update_recipe_lkup_idx(struct ice_hw *hw, struct ice_update_recipe_lkup_idx_params *params); void ice_change_proto_id_to_dvm(void); +struct ice_vsi_list_map_info * +ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, + u16 *vsi_list_id); +int ice_alloc_recipe(struct ice_hw *hw, u16 *rid); +int ice_aq_get_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd); +int ice_aq_add_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 num_recipes, struct ice_sq_cd *cd); +int +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd); +int +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd); + #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index b54052ef6050..37b54db91df2 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -7,6 +7,8 @@ #include "ice_lib.h" #include "ice_protocol_type.h" +#define ICE_TC_METADATA_LKUP_IDX 0 + /** * ice_tc_count_lkups - determine lookup count for switch filter * @flags: TC-flower flags @@ -19,7 +21,13 @@ static int ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, struct ice_tc_flower_fltr *fltr) { - int lkups_cnt = 0; + int lkups_cnt = 1; /* 0th lookup is metadata */ + + /* Always add metadata as the 0th lookup. Included elements: + * - Direction flag (always present) + * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) + * - Tunnel flag (present if tunnel) + */ if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -54,10 +62,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO)) lkups_cnt++; - /* is VLAN TPID specified */ - if (flags & ICE_TC_FLWR_FIELD_VLAN_TPID) - lkups_cnt++; - /* is CVLAN specified? */ if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) lkups_cnt++; @@ -84,10 +88,6 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, ICE_TC_FLWR_FIELD_SRC_L4_PORT)) lkups_cnt++; - /* matching for tunneled packets in metadata */ - if (fltr->tunnel_type != TNL_LAST) - lkups_cnt++; - return lkups_cnt; } @@ -176,10 +176,9 @@ static u16 ice_check_supported_vlan_tpid(u16 vlan_tpid) static int ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, - struct ice_adv_lkup_elem *list) + struct ice_adv_lkup_elem *list, int i) { struct ice_tc_flower_lyr_2_4_hdrs *hdr = &fltr->outer_headers; - int i = 0; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) { u32 tenant_id; @@ -329,8 +328,7 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, } /* always fill matching on tunneled packets in metadata */ - ice_rule_add_tunnel_metadata(&list[i]); - i++; + ice_rule_add_tunnel_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); return i; } @@ -358,13 +356,16 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; bool inner = false; u16 vlan_tpid = 0; - int i = 0; + int i = 1; /* 0th lookup is metadata */ rule_info->vlan_type = vlan_tpid; + /* Always add direction metadata */ + ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { - i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list); + i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); headers = &tc_fltr->inner_headers; inner = true; @@ -431,8 +432,7 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, rule_info->vlan_type = ice_check_supported_vlan_tpid(vlan_tpid); - ice_rule_add_vlan_metadata(&list[i]); - i++; + ice_rule_add_vlan_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); } if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) { @@ -750,17 +750,16 @@ exit: /** * ice_locate_vsi_using_queue - locate VSI using queue (forward to queue action) * @vsi: Pointer to VSI - * @tc_fltr: Pointer to tc_flower_filter + * @queue: Queue index * - * Locate the VSI using specified queue. When ADQ is not enabled, always - * return input VSI, otherwise locate corresponding VSI based on per channel - * offset and qcount + * Locate the VSI using specified "queue". When ADQ is not enabled, + * always return input VSI, otherwise locate corresponding + * VSI based on per channel "offset" and "qcount" */ -static struct ice_vsi * -ice_locate_vsi_using_queue(struct ice_vsi *vsi, - struct ice_tc_flower_fltr *tc_fltr) +struct ice_vsi * +ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue) { - int num_tc, tc, queue; + int num_tc, tc; /* if ADQ is not active, passed VSI is the candidate VSI */ if (!ice_is_adq_active(vsi->back)) @@ -770,7 +769,6 @@ ice_locate_vsi_using_queue(struct ice_vsi *vsi, * upon queue number) */ num_tc = vsi->mqprio_qopt.qopt.num_tc; - queue = tc_fltr->action.fwd.q.queue; for (tc = 0; tc < num_tc; tc++) { int qcount = vsi->mqprio_qopt.qopt.count[tc]; @@ -812,6 +810,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) struct ice_pf *pf = vsi->back; struct device *dev; u32 tc_class; + int q; dev = ice_pf_to_dev(pf); @@ -840,7 +839,8 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr) /* Determine destination VSI even though the action is * FWD_TO_QUEUE, because QUEUE is associated with VSI */ - dest_vsi = tc_fltr->dest_vsi; + q = tc_fltr->action.fwd.q.queue; + dest_vsi = ice_locate_vsi_using_queue(vsi, q); break; default: dev_err(dev, @@ -1343,24 +1343,24 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, dissector = rule->match.dissector; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_CVLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | - BIT(FLOW_DISSECTOR_KEY_IP) | - BIT(FLOW_DISSECTOR_KEY_ENC_IP) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_PPPOE) | - BIT(FLOW_DISSECTOR_KEY_L2TPV3))) { + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PPPOE) | + BIT_ULL(FLOW_DISSECTOR_KEY_L2TPV3))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used"); return -EOPNOTSUPP; } @@ -1382,10 +1382,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, */ headers = &fltr->inner_headers; } else if (dissector->used_keys & - (BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { @@ -1716,7 +1716,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, /* If ADQ is configured, and the queue belongs to ADQ VSI, then prepare * ADQ switch filter */ - ch_vsi = ice_locate_vsi_using_queue(vsi, fltr); + ch_vsi = ice_locate_vsi_using_queue(vsi, fltr->action.fwd.q.queue); if (!ch_vsi) return -EINVAL; fltr->dest_vsi = ch_vsi; diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 8bbc1a62bdb1..65d387163a46 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -204,6 +204,7 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf) return pf->num_dmac_chnl_fltrs; } +struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue); int ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, struct flow_cls_offload *cls_flower); diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index ae98d5a8ff60..b2f5c9fe0149 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -21,6 +21,7 @@ #define _ICE_TRACE_H_ #include <linux/tracepoint.h> +#include "ice_eswitch_br.h" /* ice_trace() macro enables shared code to refer to trace points * like: @@ -240,6 +241,95 @@ DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_req); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_fw_done); DEFINE_TX_TSTAMP_OP_EVENT(ice_tx_tstamp_complete); +DECLARE_EVENT_CLASS(ice_esw_br_fdb_template, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb), + TP_STRUCT__entry(__array(char, dev_name, IFNAMSIZ) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __field(int, flags)), + TP_fast_assign(strscpy(__entry->dev_name, + netdev_name(fdb->dev), + IFNAMSIZ); + memcpy(__entry->addr, fdb->data.addr, ETH_ALEN); + __entry->vid = fdb->data.vid; + __entry->flags = fdb->flags;), + TP_printk("net_device=%s addr=%pM vid=%u flags=%x", + __entry->dev_name, + __entry->addr, + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_create, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DEFINE_EVENT(ice_esw_br_fdb_template, + ice_eswitch_br_fdb_entry_find_and_delete, + TP_PROTO(struct ice_esw_br_fdb_entry *fdb), + TP_ARGS(fdb) +); + +DECLARE_EVENT_CLASS(ice_esw_br_vlan_template, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan), + TP_STRUCT__entry(__field(u16, vid) + __field(u16, flags)), + TP_fast_assign(__entry->vid = vlan->vid; + __entry->flags = vlan->flags;), + TP_printk("vid=%u flags=%x", + __entry->vid, + __entry->flags) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_create, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +DEFINE_EVENT(ice_esw_br_vlan_template, + ice_eswitch_br_vlan_cleanup, + TP_PROTO(struct ice_esw_br_vlan *vlan), + TP_ARGS(vlan) +); + +#define ICE_ESW_BR_PORT_NAME_L 16 + +DECLARE_EVENT_CLASS(ice_esw_br_port_template, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port), + TP_STRUCT__entry(__field(u16, vport_num) + __array(char, port_type, ICE_ESW_BR_PORT_NAME_L)), + TP_fast_assign(__entry->vport_num = port->vsi_idx; + if (port->type == ICE_ESWITCH_BR_UPLINK_PORT) + strscpy(__entry->port_type, + "Uplink", + ICE_ESW_BR_PORT_NAME_L); + else + strscpy(__entry->port_type, + "VF Representor", + ICE_ESW_BR_PORT_NAME_L);), + TP_printk("vport_num=%u port type=%s", + __entry->vport_num, + __entry->port_type) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_link, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + +DEFINE_EVENT(ice_esw_br_port_template, + ice_eswitch_br_port_unlink, + TP_PROTO(struct ice_esw_br_port *port), + TP_ARGS(port) +); + /* End tracepoints */ #endif /* _ICE_TRACE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a09556e57803..5e353b0cbe6f 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -277,6 +277,8 @@ struct ice_hw_common_caps { u8 dcb; u8 ieee_1588; u8 rdma; + u8 roce_lag; + u8 sriov_lag; bool nvm_update_pending_nvm; bool nvm_update_pending_orom; @@ -1033,14 +1035,15 @@ enum ice_sw_fwd_act_type { ICE_FWD_TO_Q, ICE_FWD_TO_QGRP, ICE_DROP_PACKET, + ICE_NOP, ICE_INVAL_ACT }; struct ice_aq_get_set_rss_lut_params { - u16 vsi_handle; /* software VSI handle */ - u16 lut_size; /* size of the LUT buffer */ - u8 lut_type; /* type of the LUT (i.e. VSI, PF, Global) */ u8 *lut; /* input RSS LUT for set and output RSS LUT for get */ + enum ice_lut_size lut_size; /* size of the LUT buffer */ + enum ice_lut_type lut_type; /* type of the LUT (i.e. VSI, PF, Global) */ + u16 vsi_handle; /* software VSI handle */ u8 global_lut_id; /* only valid when lut_type is global */ }; @@ -1142,9 +1145,6 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_SR_WORDS_IN_1KB 512 -/* Hash redirection LUT for VSI - maximum array size */ -#define ICE_VSIQF_HLUT_ARRAY_SIZE ((VSIQF_HLUT_MAX_INDEX + 1) * 4) - /* AQ API version for LLDP_FILTER_CONTROL */ #define ICE_FW_API_LLDP_FLTR_MAJ 1 #define ICE_FW_API_LLDP_FLTR_MIN 7 diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index b26ce4425f45..24e4f4d897b6 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -186,25 +186,6 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) } /** - * ice_check_vf_ready_for_reset - check if VF is ready to be reset - * @vf: VF to check if it's ready to be reset - * - * The purpose of this function is to ensure that the VF is not in reset, - * disabled, and is both initialized and active, thus enabling us to safely - * initialize another reset. - */ -int ice_check_vf_ready_for_reset(struct ice_vf *vf) -{ - int ret; - - ret = ice_check_vf_ready_for_cfg(vf); - if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) - ret = -EAGAIN; - - return ret; -} - -/** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure * @is_vflr: true if VFLR was issued, false if not @@ -323,6 +304,237 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) } /** + * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN + * @vf: VF to add MAC filters for + * @vsi: Pointer to VSI + * + * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver + * always re-adds either a VLAN 0 or port VLAN based filter after reset. + */ +static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct device *dev = ice_pf_to_dev(vf->pf); + int err; + + if (ice_vf_is_port_vlan_ena(vf)) { + err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info); + if (err) { + dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n", + vf->vf_id, err); + return err; + } + + err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); + } else { + err = ice_vsi_add_vlan_zero(vsi); + } + + if (err) { + dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n", + ice_vf_is_port_vlan_ena(vf) ? + ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err); + return err; + } + + err = vlan_ops->ena_rx_filtering(vsi); + if (err) + dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n", + vf->vf_id, vsi->idx, err); + + return 0; +} + +/** + * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration + * @vf: VF to re-apply the configuration for + * + * Called after a VF VSI has been re-added/rebuild during reset. The PF driver + * needs to re-apply the host configured Tx rate limiting configuration. + */ +static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + int err; + + if (WARN_ON(!vsi)) + return -EINVAL; + + if (vf->min_tx_rate) { + err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n", + vf->min_tx_rate, vf->vf_id, err); + return err; + } + } + + if (vf->max_tx_rate) { + err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000); + if (err) { + dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n", + vf->max_tx_rate, vf->vf_id, err); + return err; + } + } + + return 0; +} + +/** + * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value + * @vf: VF to configure trust setting for + */ +static void ice_vf_set_host_trust_cfg(struct ice_vf *vf) +{ + assign_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps, vf->trusted); +} + +/** + * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA + * @vf: VF to add MAC filters for + * + * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver + * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset. + */ +static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + u8 broadcast[ETH_ALEN]; + int status; + + if (WARN_ON(!vsi)) + return -EINVAL; + + if (ice_is_eswitch_mode_switchdev(vf->pf)) + return 0; + + eth_broadcast_addr(broadcast); + status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); + if (status) { + dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n", + vf->vf_id, status); + return status; + } + + vf->num_mac++; + + if (is_valid_ether_addr(vf->hw_lan_addr)) { + status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, + ICE_FWD_TO_VSI); + if (status) { + dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", + &vf->hw_lan_addr[0], vf->vf_id, + status); + return status; + } + vf->num_mac++; + + ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); + } + + return 0; +} + +/** + * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config + * @vsi: Pointer to VSI + * + * This function moves VSI into corresponding scheduler aggregator node + * based on cached value of "aggregator node info" per VSI + */ +static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct device *dev; + int status; + + if (!vsi->agg_node) + return; + + dev = ice_pf_to_dev(pf); + if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) { + dev_dbg(dev, + "agg_id %u already has reached max_num_vsis %u\n", + vsi->agg_node->agg_id, vsi->agg_node->num_vsis); + return; + } + + status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id, + vsi->idx, vsi->tc_cfg.ena_tc); + if (status) + dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node", + vsi->idx, vsi->agg_node->agg_id); + else + vsi->agg_node->num_vsis++; +} + +/** + * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset + * @vf: VF to rebuild host configuration on + */ +static void ice_vf_rebuild_host_cfg(struct ice_vf *vf) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_vf_set_host_trust_cfg(vf); + + if (ice_vf_rebuild_host_mac_cfg(vf)) + dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n", + vf->vf_id); + + if (ice_vf_rebuild_host_vlan_cfg(vf, vsi)) + dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", + vf->vf_id); + + if (ice_vf_rebuild_host_tx_rate_cfg(vf)) + dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", + vf->vf_id); + + if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk)) + dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n", + vf->vf_id); + + /* rebuild aggregator node config for main VF VSI */ + ice_vf_rebuild_aggregator_node_cfg(vsi); +} + +/** + * ice_set_vf_state_qs_dis - Set VF queues state to disabled + * @vf: pointer to the VF structure + */ +static void ice_set_vf_state_qs_dis(struct ice_vf *vf) +{ + /* Clear Rx/Tx enabled queues flag */ + bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); + bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); + clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); +} + +/** + * ice_vf_set_initialized - VF is ready for VIRTCHNL communication + * @vf: VF to set in initialized state + * + * After this function the VF will be ready to receive/handle the + * VIRTCHNL_OP_GET_VF_RESOURCES message + */ +static void ice_vf_set_initialized(struct ice_vf *vf) +{ + ice_set_vf_state_qs_dis(vf); + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_DIS, vf->vf_states); + set_bit(ICE_VF_STATE_INIT, vf->vf_states); + memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); +} + +/** * ice_vf_post_vsi_rebuild - Reset tasks that occur after VSI rebuild * @vf: the VF being reset * @@ -631,11 +843,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; } + if (flags & ICE_VF_RESET_LOCK) + mutex_lock(&vf->cfg_lock); + else + lockdep_assert_held(&vf->cfg_lock); + if (ice_is_vf_disabled(vf)) { vsi = ice_get_vf_vsi(vf); if (!vsi) { dev_dbg(dev, "VF is already removed\n"); - return -EINVAL; + err = -EINVAL; + goto out_unlock; } ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); @@ -644,14 +862,9 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n", vf->vf_id); - return 0; + goto out_unlock; } - if (flags & ICE_VF_RESET_LOCK) - mutex_lock(&vf->cfg_lock); - else - lockdep_assert_held(&vf->cfg_lock); - /* Set VF disable bit state here, before triggering reset */ set_bit(ICE_VF_STATE_DIS, vf->vf_states); ice_trigger_vf_reset(vf, flags & ICE_VF_RESET_VFLR, false); @@ -726,18 +939,6 @@ out_unlock: } /** - * ice_set_vf_state_qs_dis - Set VF queues state to disabled - * @vf: pointer to the VF structure - */ -static void ice_set_vf_state_qs_dis(struct ice_vf *vf) -{ - /* Clear Rx/Tx enabled queues flag */ - bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); - bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); - clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); -} - -/** * ice_set_vf_state_dis - Set VF state to disabled * @vf: pointer to the VF structure */ @@ -978,211 +1179,6 @@ bool ice_is_vf_link_up(struct ice_vf *vf) } /** - * ice_vf_set_host_trust_cfg - set trust setting based on pre-reset value - * @vf: VF to configure trust setting for - */ -static void ice_vf_set_host_trust_cfg(struct ice_vf *vf) -{ - if (vf->trusted) - set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); - else - clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); -} - -/** - * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA - * @vf: VF to add MAC filters for - * - * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver - * always re-adds a broadcast filter and the VF's perm_addr/LAA after reset. - */ -static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - u8 broadcast[ETH_ALEN]; - int status; - - if (WARN_ON(!vsi)) - return -EINVAL; - - if (ice_is_eswitch_mode_switchdev(vf->pf)) - return 0; - - eth_broadcast_addr(broadcast); - status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); - if (status) { - dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n", - vf->vf_id, status); - return status; - } - - vf->num_mac++; - - if (is_valid_ether_addr(vf->hw_lan_addr)) { - status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, - ICE_FWD_TO_VSI); - if (status) { - dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", - &vf->hw_lan_addr[0], vf->vf_id, - status); - return status; - } - vf->num_mac++; - - ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); - } - - return 0; -} - -/** - * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN - * @vf: VF to add MAC filters for - * @vsi: Pointer to VSI - * - * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver - * always re-adds either a VLAN 0 or port VLAN based filter after reset. - */ -static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) -{ - struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); - struct device *dev = ice_pf_to_dev(vf->pf); - int err; - - if (ice_vf_is_port_vlan_ena(vf)) { - err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info); - if (err) { - dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n", - vf->vf_id, err); - return err; - } - - err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); - } else { - err = ice_vsi_add_vlan_zero(vsi); - } - - if (err) { - dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n", - ice_vf_is_port_vlan_ena(vf) ? - ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err); - return err; - } - - err = vlan_ops->ena_rx_filtering(vsi); - if (err) - dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n", - vf->vf_id, vsi->idx, err); - - return 0; -} - -/** - * ice_vf_rebuild_host_tx_rate_cfg - re-apply the Tx rate limiting configuration - * @vf: VF to re-apply the configuration for - * - * Called after a VF VSI has been re-added/rebuild during reset. The PF driver - * needs to re-apply the host configured Tx rate limiting configuration. - */ -static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - int err; - - if (WARN_ON(!vsi)) - return -EINVAL; - - if (vf->min_tx_rate) { - err = ice_set_min_bw_limit(vsi, (u64)vf->min_tx_rate * 1000); - if (err) { - dev_err(dev, "failed to set min Tx rate to %d Mbps for VF %u, error %d\n", - vf->min_tx_rate, vf->vf_id, err); - return err; - } - } - - if (vf->max_tx_rate) { - err = ice_set_max_bw_limit(vsi, (u64)vf->max_tx_rate * 1000); - if (err) { - dev_err(dev, "failed to set max Tx rate to %d Mbps for VF %u, error %d\n", - vf->max_tx_rate, vf->vf_id, err); - return err; - } - } - - return 0; -} - -/** - * ice_vf_rebuild_aggregator_node_cfg - rebuild aggregator node config - * @vsi: Pointer to VSI - * - * This function moves VSI into corresponding scheduler aggregator node - * based on cached value of "aggregator node info" per VSI - */ -static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - int status; - - if (!vsi->agg_node) - return; - - dev = ice_pf_to_dev(pf); - if (vsi->agg_node->num_vsis == ICE_MAX_VSIS_IN_AGG_NODE) { - dev_dbg(dev, - "agg_id %u already has reached max_num_vsis %u\n", - vsi->agg_node->agg_id, vsi->agg_node->num_vsis); - return; - } - - status = ice_move_vsi_to_agg(pf->hw.port_info, vsi->agg_node->agg_id, - vsi->idx, vsi->tc_cfg.ena_tc); - if (status) - dev_dbg(dev, "unable to move VSI idx %u into aggregator %u node", - vsi->idx, vsi->agg_node->agg_id); - else - vsi->agg_node->num_vsis++; -} - -/** - * ice_vf_rebuild_host_cfg - host admin configuration is persistent across reset - * @vf: VF to rebuild host configuration on - */ -void ice_vf_rebuild_host_cfg(struct ice_vf *vf) -{ - struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - if (WARN_ON(!vsi)) - return; - - ice_vf_set_host_trust_cfg(vf); - - if (ice_vf_rebuild_host_mac_cfg(vf)) - dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n", - vf->vf_id); - - if (ice_vf_rebuild_host_vlan_cfg(vf, vsi)) - dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", - vf->vf_id); - - if (ice_vf_rebuild_host_tx_rate_cfg(vf)) - dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", - vf->vf_id); - - if (ice_vsi_apply_spoofchk(vsi, vf->spoofchk)) - dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n", - vf->vf_id); - - /* rebuild aggregator node config for main VF VSI */ - ice_vf_rebuild_aggregator_node_cfg(vsi); -} - -/** * ice_vf_ctrl_invalidate_vsi - invalidate ctrl_vsi_idx to remove VSI access * @vf: VF that control VSI is being invalidated on */ @@ -1311,23 +1307,6 @@ void ice_vf_vsi_release(struct ice_vf *vf) } /** - * ice_vf_set_initialized - VF is ready for VIRTCHNL communication - * @vf: VF to set in initialized state - * - * After this function the VF will be ready to receive/handle the - * VIRTCHNL_OP_GET_VF_RESOURCES message - */ -void ice_vf_set_initialized(struct ice_vf *vf) -{ - ice_set_vf_state_qs_dis(vf); - clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); - clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); - clear_bit(ICE_VF_STATE_DIS, vf->vf_states); - set_bit(ICE_VF_STATE_INIT, vf->vf_states); - memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); -} - -/** * ice_get_vf_ctrl_vsi - Get first VF control VSI pointer * @pf: the PF private structure * @vsi: pointer to the VSI diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 67172fdd9bc2..48fea6fa0362 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -215,7 +215,6 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); -int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 6f3293b793b5..0c7e77c0a09f 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -32,13 +32,11 @@ int ice_vsi_apply_spoofchk(struct ice_vsi *vsi, bool enable); bool ice_is_vf_trusted(struct ice_vf *vf); bool ice_vf_has_no_qs_ena(struct ice_vf *vf); bool ice_is_vf_link_up(struct ice_vf *vf); -void ice_vf_rebuild_host_cfg(struct ice_vf *vf); void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf); void ice_vf_ctrl_vsi_release(struct ice_vf *vf); struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi); void ice_vf_invalidate_vsi(struct ice_vf *vf); void ice_vf_vsi_release(struct ice_vf *vf); -void ice_vf_set_initialized(struct ice_vf *vf); #endif /* _ICE_VF_LIB_PRIVATE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index b1ffb81893d4..d7b10dc67f03 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -21,6 +21,99 @@ noop_vlan(struct ice_vsi __always_unused *vsi) return 0; } +static void ice_port_vlan_on(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + /* setup outer VLAN ops */ + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + vlan_ops->add_vlan = noop_vlan_arg; + vlan_ops->del_vlan = noop_vlan_arg; + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + } else { + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; + } + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; +} + +static void ice_port_vlan_off(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + } else { + vlan_ops->del_vlan = ice_vsi_del_vlan; + } + + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) + vlan_ops->ena_rx_filtering = noop_vlan; + else + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; +} + +/** + * ice_vf_vsi_enable_port_vlan - Set VSI VLAN ops to support port VLAN + * @vsi: VF's VSI being configured + * + * The function won't create port VLAN, it only allows to create port VLAN + * using VLAN ops on the VF VSI. + */ +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_on(vsi); +} + +/** + * ice_vf_vsi_disable_port_vlan - Clear VSI support for creating port VLAN + * @vsi: VF's VSI being configured + * + * The function should be called after removing port VLAN on VSI + * (using VLAN ops) + */ +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) +{ + if (WARN_ON_ONCE(!vsi->vf)) + return; + + ice_port_vlan_off(vsi); +} + /** * ice_vf_vsi_init_vlan_ops - Initialize default VSI VLAN ops for VF VSI * @vsi: VF's VSI being configured @@ -39,91 +132,18 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) if (WARN_ON(!vf)) return; - if (ice_is_dvm_ena(&pf->hw)) { - vlan_ops = &vsi->outer_vlan_ops; + if (ice_vf_is_port_vlan_ena(vf)) + ice_port_vlan_on(vsi); + else + ice_port_vlan_off(vsi); - /* outer VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - /* setup outer VLAN ops */ - vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - vlan_ops->add_vlan = noop_vlan_arg; - vlan_ops->del_vlan = noop_vlan_arg; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; - - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; - - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } else { - vlan_ops = &vsi->inner_vlan_ops; + vlan_ops = ice_is_dvm_ena(&pf->hw) ? + &vsi->outer_vlan_ops : &vsi->inner_vlan_ops; - /* inner VLAN ops regardless of port VLAN config */ - vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; - vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; - vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; - - if (ice_vf_is_port_vlan_ena(vf)) { - vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - /* all Rx traffic should be in the domain of the - * assigned port VLAN, so prevent disabling Rx VLAN - * filtering - */ - vlan_ops->dis_rx_filtering = noop_vlan; - } else { - vlan_ops->dis_rx_filtering = - ice_vsi_dis_rx_vlan_filtering; - if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) - vlan_ops->ena_rx_filtering = noop_vlan; - else - vlan_ops->ena_rx_filtering = - ice_vsi_ena_rx_vlan_filtering; - - vlan_ops->del_vlan = ice_vsi_del_vlan; - vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; - vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; - vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; - vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } - } + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; + vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h index 875a4e615f39..df8aa09df3e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h @@ -13,7 +13,11 @@ void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi); #ifdef CONFIG_PCI_IOV void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi); +void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi); +void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi); #else static inline void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_enable_port_vlan(struct ice_vsi *vsi) { } +static inline void ice_vf_vsi_disable_port_vlan(struct ice_vsi *vsi) { } #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_PF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index efbc2968a7bf..b03426ac932b 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -428,7 +428,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) goto err; } - len = sizeof(struct virtchnl_vf_resource); + len = virtchnl_struct_size(vfres, vsi_res, 0); vfres = kzalloc(len, GFP_KERNEL); if (!vfres) { @@ -500,7 +500,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->num_queue_pairs = vsi->num_txq; vfres->max_vectors = vf->pf->vfs.num_msix_per; vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; - vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vfres->rss_lut_size = ICE_LUT_VSI_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; @@ -962,7 +962,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + if (vrl->lut_entries != ICE_LUT_VSI_SIZE) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -978,7 +978,7 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - if (ice_set_rss_lut(vsi, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE)) + if (ice_set_rss_lut(vsi, vrl->lut, ICE_LUT_VSI_SIZE)) v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; error_param: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret, @@ -1724,6 +1724,8 @@ error_param: vf->vf_id, i); } + ice_lag_move_new_vf_nodes(vf); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0); @@ -3947,7 +3949,6 @@ error_handler: ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 5b4a0abb4607..76266e709a39 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -202,6 +202,24 @@ int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi) return ice_vsi_manage_vlan_insertion(vsi); } +static void +ice_save_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + vlan->sw_flags2 = info->sw_flags2; + vlan->inner_vlan_flags = info->inner_vlan_flags; + vlan->outer_vlan_flags = info->outer_vlan_flags; +} + +static void +ice_restore_vlan_info(struct ice_aqc_vsi_props *info, + struct ice_vsi_vlan_info *vlan) +{ + info->sw_flags2 = vlan->sw_flags2; + info->inner_vlan_flags = vlan->inner_vlan_flags; + info->outer_vlan_flags = vlan->outer_vlan_flags; +} + /** * __ice_vsi_set_inner_port_vlan - set port VLAN VSI context settings to enable a port VLAN * @vsi: the VSI to update @@ -218,6 +236,7 @@ static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; info = &ctxt->info; info->inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED | @@ -259,6 +278,33 @@ int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_inner_port_vlan(vsi, port_vlan_info); } +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_aqc_vsi_props *info; + struct ice_vsi_ctx *ctxt; + int ret; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_inner_vlan = 0; + ctxt->info = vsi->info; + info = &ctxt->info; + info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) + dev_err(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return ret; +} + /** * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI * @vsi: VSI to enable or disable VLAN pruning on @@ -647,6 +693,7 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) if (!ctxt) return -ENOMEM; + ice_save_vlan_info(&vsi->info, &vsi->vlan_info); ctxt->info = vsi->info; ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; @@ -689,9 +736,6 @@ __ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) * used if DVM is supported. Also, this function should never be called directly * as it should be part of ice_vsi_vlan_ops if it's needed. * - * This function does not support clearing the port VLAN as there is currently - * no use case for this. - * * Use the ice_vlan structure passed in to set this VSI in a port VLAN. */ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) @@ -705,3 +749,37 @@ int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return __ice_vsi_set_outer_port_vlan(vsi, port_vlan_info, vlan->tpid); } + +/** + * ice_vsi_clear_outer_port_vlan - clear outer port vlan + * @vsi: VSI to configure + * + * The function is restoring previously set vlan config (saved in + * vsi->vlan_info). Setting happens in port vlan configuration. + */ +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ice_restore_vlan_info(&vsi->info, &vsi->vlan_info); + vsi->info.port_based_outer_vlan = 0; + ctxt->info = vsi->info; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for clearing outer port based VLAN failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + + kfree(ctxt); + return err; +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h index f459909490ec..f0d84d11bd5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h @@ -7,6 +7,12 @@ #include <linux/types.h> #include "ice_vlan.h" +struct ice_vsi_vlan_info { + u8 sw_flags2; + u8 inner_vlan_flags; + u8 outer_vlan_flags; +}; + struct ice_vsi; int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); @@ -17,6 +23,7 @@ int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi); int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi); int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_inner_port_vlan(struct ice_vsi *vsi); int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi); int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi); @@ -28,5 +35,6 @@ int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi); int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid); int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi); int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_clear_outer_port_vlan(struct ice_vsi *vsi); #endif /* _ICE_VSI_VLAN_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h index 5b47568f6256..b2d2330dedcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h @@ -21,6 +21,7 @@ struct ice_vsi_vlan_ops { int (*ena_tx_filtering)(struct ice_vsi *vsi); int (*dis_tx_filtering)(struct ice_vsi *vsi); int (*set_port_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*clear_port_vlan)(struct ice_vsi *vsi); }; void ice_vsi_init_vlan_ops(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a7fe2b4ce655..2a3f0834e139 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -546,19 +546,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) } /** - * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring - * @rx_ring: Rx ring - */ -static void ice_bump_ntc(struct ice_rx_ring *rx_ring) -{ - int ntc = rx_ring->next_to_clean + 1; - - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - prefetch(ICE_RX_DESC(rx_ring, ntc)); -} - -/** * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer * @rx_ring: Rx ring * @xdp: Pointer to XDP buffer @@ -572,8 +559,14 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; + struct skb_shared_info *sinfo = NULL; struct sk_buff *skb; + u32 nr_frags = 0; + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } net_prefetch(xdp->data_meta); skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, @@ -589,6 +582,29 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) __skb_pull(skb, metasize); } + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + for (int i = 0; i < nr_frags; i++) { + struct skb_shared_info *skinfo = skb_shinfo(skb); + skb_frag_t *frag = &sinfo->frags[i]; + struct page *page; + void *addr; + + page = dev_alloc_page(); + if (!page) { + dev_kfree_skb(skb); + return NULL; + } + addr = page_to_virt(page); + + memcpy(addr, skb_frag_page(frag), skb_frag_size(frag)); + + __skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++, + addr, 0, skb_frag_size(frag)); + } + +out: xsk_buff_free(xdp); return skb; } @@ -597,7 +613,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring */ -static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) { u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *tx_desc; @@ -619,7 +635,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) } if (!completed_frames) - return; + return 0; if (likely(!xdp_ring->xdp_tx_active)) { xsk_frames = completed_frames; @@ -649,6 +665,8 @@ skip: xdp_ring->next_to_clean -= cnt; if (xsk_frames) xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + + return completed_frames; } /** @@ -666,37 +684,72 @@ skip: static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) { + struct skb_shared_info *sinfo = NULL; u32 size = xdp->data_end - xdp->data; u32 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; - dma_addr_t dma; - - if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) { - ice_clean_xdp_irq_zc(xdp_ring); - if (!ICE_DESC_UNUSED(xdp_ring)) { - xdp_ring->ring_stats->tx_stats.tx_busy++; - return ICE_XDP_CONSUMED; - } + struct xdp_buff *head; + u32 nr_frags = 0; + u32 free_space; + u32 frag = 0; + + free_space = ICE_DESC_UNUSED(xdp_ring); + if (free_space < ICE_RING_QUARTER(xdp_ring)) + free_space += ice_clean_xdp_irq_zc(xdp_ring); + + if (unlikely(!free_space)) + goto busy; + + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + if (free_space < nr_frags + 1) + goto busy; } - dma = xsk_buff_xdp_get_dma(xdp); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); - - tx_buf = &xdp_ring->tx_buf[ntu]; - tx_buf->xdp = xdp; - tx_buf->type = ICE_TX_BUF_XSK_TX; tx_desc = ICE_TX_DESC(xdp_ring, ntu); - tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, - 0, size, 0); - xdp_ring->xdp_tx_active++; + tx_buf = &xdp_ring->tx_buf[ntu]; + head = xdp; + + for (;;) { + dma_addr_t dma; + + dma = xsk_buff_xdp_get_dma(xdp); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + + tx_buf->xdp = xdp; + tx_buf->type = ICE_TX_BUF_XSK_TX; + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0); + /* account for each xdp_buff from xsk_buff_pool */ + xdp_ring->xdp_tx_active++; + + if (++ntu == xdp_ring->count) + ntu = 0; + + if (frag == nr_frags) + break; + + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_buf = &xdp_ring->tx_buf[ntu]; + + xdp = xsk_buff_get_frag(head); + size = skb_frag_size(&sinfo->frags[frag]); + frag++; + } - if (++ntu == xdp_ring->count) - ntu = 0; xdp_ring->next_to_use = ntu; + /* update last descriptor from a frame with EOP */ + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S); return ICE_XDP_TX; + +busy: + xdp_ring->ring_stats->tx_stats.tx_busy++; + + return ICE_XDP_CONSUMED; } /** @@ -752,6 +805,34 @@ out_failure: return result; } +static int +ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, + struct xdp_buff *xdp, const unsigned int size) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(first); + + if (!size) + return 0; + + if (!xdp_buff_has_frags(first)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(first); + } + + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { + xsk_buff_free(first); + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, + virt_to_page(xdp->data_hard_start), 0, size); + sinfo->xdp_frags_size += size; + xsk_buff_add_frag(xdp); + + return 0; +} + /** * ice_clean_rx_irq_zc - consumes packets from the hardware ring * @rx_ring: AF_XDP Rx ring @@ -762,9 +843,14 @@ out_failure: int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool; + u32 ntc = rx_ring->next_to_clean; + u32 ntu = rx_ring->next_to_use; + struct xdp_buff *first = NULL; struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; + u32 cnt = rx_ring->count; bool failure = false; int entries_to_alloc; @@ -774,6 +860,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) xdp_prog = READ_ONCE(rx_ring->xdp_prog); xdp_ring = rx_ring->xdp_ring; + if (ntc != rx_ring->first_desc) + first = *ice_xdp_buf(rx_ring, rx_ring->first_desc); + while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; @@ -783,7 +872,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) u16 vlan_tag = 0; u16 rx_ptype; - rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = ICE_RX_DESC(rx_ring, ntc); stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) @@ -795,51 +884,61 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) */ dma_rmb(); - if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use)) + if (unlikely(ntc == ntu)) break; - xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean); + xdp = *ice_xdp_buf(rx_ring, ntc); size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; - if (!size) { - xdp->data = NULL; - xdp->data_end = NULL; - xdp->data_hard_start = NULL; - xdp->data_meta = NULL; - goto construct_skb; - } xsk_buff_set_size(xdp, size); - xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(xdp, xsk_pool); + + if (!first) { + first = xdp; + xdp_buff_clear_frags_flag(first); + } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { + break; + } + + if (++ntc == cnt) + ntc = 0; - xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring); + if (ice_is_non_eop(rx_ring, rx_desc)) + continue; + + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { xdp_xmit |= xdp_res; } else if (xdp_res == ICE_XDP_EXIT) { failure = true; + first = NULL; + rx_ring->first_desc = ntc; break; } else if (xdp_res == ICE_XDP_CONSUMED) { - xsk_buff_free(xdp); + xsk_buff_free(first); } else if (xdp_res == ICE_XDP_PASS) { goto construct_skb; } - total_rx_bytes += size; + total_rx_bytes += xdp_get_buff_len(first); total_rx_packets++; - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; continue; construct_skb: /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, xdp); + skb = ice_construct_skb_zc(rx_ring, first); if (!skb) { rx_ring->ring_stats->rx_stats.alloc_buf_failed++; break; } - ice_bump_ntc(rx_ring); + first = NULL; + rx_ring->first_desc = ntc; if (eth_skb_pad(skb)) { skb = NULL; @@ -858,18 +957,22 @@ construct_skb: ice_receive_skb(rx_ring, skb, vlan_tag); } - entries_to_alloc = ICE_DESC_UNUSED(rx_ring); + rx_ring->next_to_clean = ntc; + entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc); ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); - if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { - if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) - xsk_set_rx_need_wakeup(rx_ring->xsk_pool); + if (xsk_uses_need_wakeup(xsk_pool)) { + /* ntu could have changed when allocating entries above, so + * use rx_ring value instead of stack based one + */ + if (failure || ntc == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(xsk_pool); else - xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); + xsk_clear_rx_need_wakeup(xsk_pool); return (int)total_rx_packets; } @@ -894,7 +997,7 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(desc), 0, desc->len, 0); *total_bytes += desc->len; @@ -921,7 +1024,7 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de tx_desc = ICE_TX_DESC(xdp_ring, ntu++); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(&descs[i]), 0, descs[i].len, 0); *total_bytes += descs[i].len; |